WO2007081147A1 - Portable terminal having camera for recognizing name card and method thererof using the same - Google Patents

Portable terminal having camera for recognizing name card and method thererof using the same Download PDF

Info

Publication number
WO2007081147A1
WO2007081147A1 PCT/KR2007/000158 KR2007000158W WO2007081147A1 WO 2007081147 A1 WO2007081147 A1 WO 2007081147A1 KR 2007000158 W KR2007000158 W KR 2007000158W WO 2007081147 A1 WO2007081147 A1 WO 2007081147A1
Authority
WO
WIPO (PCT)
Prior art keywords
field
character
name card
name
information
Prior art date
Application number
PCT/KR2007/000158
Other languages
French (fr)
Inventor
Daekeun You
In-Jung Kim
Ki-Seok Kim
Young Tae Lee
Original Assignee
Inzisoft Co., Ltd.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Inzisoft Co., Ltd. filed Critical Inzisoft Co., Ltd.
Publication of WO2007081147A1 publication Critical patent/WO2007081147A1/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40Document-oriented image-based pattern recognition
    • G06V30/41Analysis of document content
    • G06V30/412Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M1/00Substation equipment, e.g. for use by subscribers
    • H04M1/26Devices for calling a subscriber
    • H04M1/27Devices whereby a plurality of signals may be stored simultaneously
    • H04M1/274Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc
    • H04M1/2745Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc using static electronic memories, e.g. chips
    • H04M1/2753Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc using static electronic memories, e.g. chips providing data content
    • H04M1/2755Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc using static electronic memories, e.g. chips providing data content by optical scanning
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M1/00Substation equipment, e.g. for use by subscribers
    • H04M1/72Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
    • H04M1/724User interfaces specially adapted for cordless or mobile telephones
    • H04M1/72403User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M1/00Substation equipment, e.g. for use by subscribers
    • H04M1/26Devices for calling a subscriber
    • H04M1/27Devices whereby a plurality of signals may be stored simultaneously
    • H04M1/274Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc
    • H04M1/2745Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc using static electronic memories, e.g. chips
    • H04M1/27453Directories allowing storage of additional subscriber data, e.g. metadata
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M2250/00Details of telephonic subscriber devices
    • H04M2250/52Details of telephonic subscriber devices including functional features of a camera

Definitions

  • the present invention relates to a method and apparatus for recognizing a name card by using a portable terminal having a camera, and more particularly, to a method and apparatus for recognizing a name card, wherein character data can be obtained by further rapidly extracting only necessary information after a name card image is captured by using a camera.
  • a method of storing a name card in a portable terminal wherein a name card image is captured by using a camera embedded in the portable terminal, and the captured name card image undergoes character recognition by using a character recognition algorithm.
  • the character recognition is a technique in which characters recorded in an area having a specific surface such as paper are read and recognized by using a mechanical device, and the characters are converted into a code recognizable by a computer.
  • a character recognition system generally includes a photoelectric converter, a recognition processor, a memory, and an output unit.
  • the photoelectric converter converts a character recorded on the paper into a voltage waveform.
  • the character recorded on the paper having a shape of a two-dimensional figure is converted into a one-dimensional signal, for example, by a scan method of a television set, which is a time-series change of a voltage waveform.
  • the memory stores an arithmetic control program which controls the recognition processor and data through which the recognized shape is presented in a specific format.
  • the recognition processor processes an unknown character input through the photoelectric converter under the control of the program stored in the memory and compares the processed character with a standard pattern stored in the same memory, so that a character type of a character whose pattern is the most similar to the standard pattern can be recognized as a character type of the unknown character.
  • the output unit sends the recognized character to the computer or other information processors in a suitable manner.
  • Examples of the character recognition system include: an optical character reader
  • OCR optical mark reader
  • MICR magnetic ink character reader
  • FIG. 1 shows an example of a general portable terminal having a camera for recognizing a name card.
  • a camera 10 captures a name card image by means of control keys 32 and 34 included in a key pad, and the captured name card image is displayed on a screen 20.
  • the portable terminal recognizes a character from the displayed image by using a character recognition function and then extracts corresponding information.
  • the extracted information is stored as name card data. According to this function, the user can store name card information further con veniently.
  • FIG. 2 is a flowchart illustrating an example of a conventional method of recognizing a name card by using a portable terminal having a camera.
  • the portable terminal captures a name card image by using the camera 10 and reads the name card image (step SI l).
  • the portable terminal performs image processing for the read name card image.
  • the image processing is equivalent to a step in which the captured name card image is transformed to be easily recognized.
  • the examples of the image processing include binarization and noise removal.
  • the portable terminal extracts a character area from the name card image that has undergone the image processing (step S 15).
  • the portable terminal performs character recognition for the extracted character area (step S 17).
  • the portable terminal extracts each field information by using the character recognition with respect to all character areas (step S 18).
  • the portable terminal displays the lastly extracted information on the screen 20 (step S 19).
  • the present invention provides a portable terminal that can further rapidly recognize a name card by using an embedded camera and a method thereof.
  • the present invention also provides a portable terminal that can further accurately recognize a name card according to a field type by using an embedded camera and a method thereof.
  • a method of recognizing a name card by using a portable terminal having a camera comprising steps of: a) determining a character feature for each field of the name card; b) extracting a character area from a name card image captured by using the camera when in a name card recognition mode; c) extracting a candidate area for each field, which is estimated to contain information on a field to be extracted from the name card image, by using the character feature for each field; d) extracting character information of each field from the candidate area for each field according to priority of the candidate area for each field; and e) integrating each character information extracted by performing the steps c) and d) with respect to each field included in the name card.
  • the method may further comprise steps of: displaying name card data constructed with the integrated character information on a screen; and displaying the name card data modified when a command is input for modifying the displayed name card data.
  • the method may further comprise a step of storing the name card data constructed with the integrated character information and the modified name card data according to a store command.
  • the method may further comprise a step of determining an extraction field so that a field containing information to be obtained can be determined from all fields of the name card after the step of a), and in the step c), a candidate area for a field corresponding to the determined extraction field is extracted from the name card image by using the character feature for each field.
  • the fields of the name card may comprise at least one of a company logo field, a company name field, a department/title field, a name filed, and a detailed information field
  • the detailed information field comprises at least one of a zip code field, an address field, a phone number filed, a fax number field, a cell phone number field, a homepage address field, and an e-mail address field.
  • the company logo field may be located at the leftmost upper portion of the name card image
  • the company name field is located at the uppermost center portion of the name card image
  • the department/title field is located below the company name field and is displayed in small font characters divided by "/" or blank
  • the name field is located below or a right side of the department/title field and in which large characters are located in the center portion of the name card with a specific interval one by one
  • a paragraph area is located below the name field and is grouped with small characters as a candidate area for a detailed information field.
  • the detailed information field may comprise the zip code filed which is located such that a couple of three numerals are divided by "-", the address field which is located next to the zip code field and starts with a city name or a province name, the phone number field which is located below the address field and starts with a country code and a local code, the fax number field which is located below or a side of the phone number field and starts with the same country or local code with the phone number field, the cell phone number field which is located below the fax number field and starts with numbers designated to a mobile communication provider, the home page field which is displayed with characters including "http" or "www”, and the e-mail address filed which is displayed with English characters and a special character "@".
  • a portable terminal for recognizing a name card by using an embedded camera comprising: a storage unit which stores a program used to recognize the name card and setting information on a character feature for each field of the name card; a character area extracting unit which extracts a character area from a name card image captured by using the camera when in a name card recognition mode; a field candidate area extracting unit which extracts a candidate area for each field, which is estimated to contain information on a field to be extracted from the name card image, by using the character feature for each field; a character information extracting unit which extracts character information of each field from the candidate area for each field according to priority of the candidate area for each field; and a controlling unit which integrates each character information extracted from each field and stores the integration result in the storage unit as name card data.
  • the controlling unit may determine an extraction field containing information to be obtained from all fields of the name card according to the input command, and wherein the field candidate area extracting unit extracts a candidate area for a field corresponding to the determined extraction field from the name card image by using the character feature for each field.
  • controlling unit may display the integrated name card data on a screen, and the controlling unit displays the name card data modified when a command is input for modifying the displayed name card data.
  • a method of recognizing a name card by using a portable terminal having a camera comprising steps of: determining a character arrangement pattern for each field of the name card; extracting a character area from a name card image captured by using the camera when in a name card recognition mode; extracting a candidate area for each field, which is estimated to contain information on a field to be extracted from the name card image, by using information on the character arrangement pattern for each field; extracting character information by using a recognizable character recognition algorithm according to a feature of each character displayed in the extracted candidate area for each field; and integrating each extracted character information.
  • the Korean characters may be recognized and extracted from the extracted field candidate area by using a Korean recognition algorithm.
  • the English/numeral characters may be recognized and extracted from the extracted field candidate area by using a English/ numeral recognition algorithm.
  • the step of extracting candidate area for each field may comprise steps of: dividing blocks for respective character areas with respect to the extracted character area in consideration of a line space, a height of each line, and a character string arrangement method; checking a line feature for each divided block; estimating a field type according to the checked line feature; checking a character feature with respect to the each estimated field; and determining the candidate area for each field according to the character feature.
  • the fields of the name card may comprise at least one of a company logo field, a company name field, a department/title field, a name filed, and a detailed information field.
  • the detailed information field may comprise at least one of a zip code field, an address field, a phone number filed, a fax number field, a cell phone number field, a homepage address field, and an e-mail address field.
  • a character area is extracted from a captured name card image
  • a candidate area for a field containing information to be extracted is extracted by using predetermined field arrangement pattern information or character feature information for each field, and character information regarding on the extracted candidate area is extracted, thereby obtaining name card information. Therefore, the name card information can be further rapidly and accurately obtained from the name card by using character recognition.
  • a field candidate is estimated of which character information is desired to be extracted from the character area of the name card according to the character feature for each field. Therefore, name card information can be further accurately obtained from the name card by using character recognition.
  • an extraction field is predetermined of which character information is desired to be extracted from a name card, and character information is extracted only for an extracted candidate area by extracting only a candidate area for a field of which character information is desired to be extracted on the basis of setting information.
  • FIG. 1 shows an example of a general portable terminal having a camera for recognizing a name card.
  • FIG. 2 is a flowchart illustrating an example of a conventional method of recognizing a name card by using a portable terminal having a camera.
  • FIG.3 shows a general field structure of a name card according to an embodiment of the present invention.
  • FIG. 4 is a block diagram illustrating a portable terminal for rapidly and accurately recognizing a name card by using an embedded camera according to an embodiment of the present invention.
  • FIG. 5 is a flowchart illustrating a method of rapidly and accurately recognizing a name card by using a portable terminal having a camera according to an embodiment of the present invention.
  • FIG. 6 is a flowchart illustrating a step of extracting field candidate areas of FIG. 5 according to a first embodiment of the present invention.
  • FIGS. 7 to 15 illustrate various examples of an actual name card to which exemplary embodiments of the present invention can be applied.
  • FIG. 16 is a flowchart illustrating an example of extracting a candidate area for each field (step S 140) of FIG. 5 according to the first embodiment of the present invention. Best Mode for Carrying Out the Invention
  • FIG.3 shows a general field structure of a name card according to an embodiment of the present invention.
  • the name card includes a company logo field 41 located at the upper leftmost portion of the name card, a company name field 42 located at the right side of the company logo field 41 and at the uppermost portion of the name card, a name field 44 located centrally below the company name field 42 and displayed in larger and thicker characters than other surrounding characters, a department/title field 43 located at the left or right side of the name field 44, and a detailed information field located below the name field 44 and forming one paragraph with small characters.
  • the detailed information field comprises: a zip code field 45 in which a couple of three numeral characters are divided by "-", an address field 46 which starts with a city name or a province name; a phone number field 47 which starts with a local code; a fax number field 48 located below the phone number field 47, a cell phone number field 49 which starts with numbers designated to a mobile communication provider, and an e-mail address field 50 which includes "@" and English characters.
  • the character area is divided according to a field type in order to achieve fast and accurate character recognition.
  • FIG. 4 is a block diagram illustrating a portable terminal for rapidly and accurately recognizing a name card by using an embedded camera according to an embodiment of the present invention.
  • the portable terminal includes a controlling unit 100, a camera unit 120, an image processing unit 140, a display unit 160, a wireless communication unit 220, a data processing unit 240, an audio processing unit 260, a key input unit 310, a storage unit 330, a character area extracting unit 350, a field candidate area extracting unit 370, and a character information extracting unit 390.
  • the controlling unit 100 controls general operations of the portable terminal. Under the control of the controlling unit 100, information is extracted through character recognition for each field of the name card image according to the embodiment of the present invention. Furthermore, under the control of the controlling unit 100, information is extracted through character recognition with respect to each field of the name card image determined by a user.
  • the camera unit 120 captures an image through a lens.
  • the camera unit 120 includes a camera sensor which converts a captured optical signal into an electrical signal, and a signal processor which converts an analog image signal captured from the camera sensor into digital data.
  • the camera sensor is a charge coupled device (CCD) sensor.
  • the signal process may be a digital signal processor (DSP).
  • DSP digital signal processor
  • the camera sensor and the signal processor may be implemented in a separation or integration manner.
  • the camera unit 120 captures the name card image according to an input command for image capture and outputs data of the captured image of the name card to the image processing unit 140.
  • the image processing unit 140 converts the data of the name card image output from the camera unit 120 into screen data to be displayed.
  • the image processing unit 140 removes noise from the data of the name card image output from the camera unit 120 and outputs the resultant data by converting its size according to a feature and size of the display unit 160.
  • the image processing unit 140 includes an image codec to compress data of a frame image displayed in the display unit 160 by using a predetermined method or to restore the compressed data of the frame image into data of an original frame image.
  • the image codec may be a JPEG codec, an MPEG codec, or a wavelet codec.
  • the image processing unit 140 may provide an on screen display (OSD) function. In this case, the image processing unit 140 may allow display data to be displayed in a specific area of a screen under the control of the controlling unit 100.
  • OSD on screen display
  • the display unit 160 displays the name card image output from the image processing unit 140 and displays the display data output from the controlling unit 100 on the screen.
  • the display unit 160 may be a liquid crystal display (LCD).
  • the display unit 160 may include an LCD controller, a memory capable of storing image data, and an LCD display element. When the LCD is implemented using a touch screen scheme, the LCD may operate as an input unit.
  • the display unit 160 may display name card information on the screen for each field, wherein the name card information has a text format in which the name card image is converted under the control of the controlling unit 100.
  • the wireless communication unit 220 transmits/receives data for wireless communication of the portable terminal.
  • the wireless communication unit 220 includes an RF transmitter which up-converts and amplifies a frequency of a transmission signal and an RF receiver which amplifies a received signal to have a low noise and down- converts its frequency.
  • the wireless communication unit 220 converts an input signal to be transmitted into a wireless signal and then transmits the resultant signal through a wireless channel. Furthermore, the wireless communication unit 220 receives the wireless signal received through the wireless channel and converts the received signal into data to be output.
  • the data processing unit 240 includes a transmission module which codes and modulates the signal to be transmitted through the wireless channel and a receiving module which demodulates and decodes the signal received through the wireless channel.
  • the audio processing unit 260 may be constructed with a codec.
  • the codec includes a data codec which processes packet data and an audio codec which processes an audio (e.g., voice) signal.
  • the audio processing unit 260 converts a digital audio signal received to the data processing unit 240 into an analog signal through the audio codec, so that the converted signal is reproduced through a speaker.
  • the audio processing unit 260 converts an analog audio signal input from a microphone into a digital audio signal through the audio codec, so that the converted signal is output to the data processing unit 240.
  • the codec may be separately provided. Alternatively, the codec may be embedded in the controlling unit 100.
  • the audio processing unit 260 may audio-converts each field information extracted according to the name card image under the control of the controlling unit 100 so that the converted information can be output through the speaker.
  • the key input unit 310 includes a plurality of keys for inputting numeral/character information and a plurality of control keys for controlling operations of the portable terminal.
  • the key input unit 310 includes a plurality of keys for controlling the capture of the name card image and the extraction of character information for each field for captured name card image.
  • the key input unit 310 outputs an input command signal to the controlling unit 100.
  • the storage unit 330 may include a program storage unit and a data storage unit.
  • the program storage unit may include programs for controlling general operations of the portable terminal and programs required for character recognition in order to extract text information from a character image displayed in a specific area according to the present embodiment.
  • the data storage unit is used to temporarily store data produced while executing the programs.
  • the storage unit 330 stores information for setting extraction field, by which a field of information desired to be obtained from the name card is set, and each field information extracted from the name card image. Furthermore, the storage unit 330 stores field arrangement pattern information determined by analyzing a general type of name cards.
  • the character area extracting unit 350 extracts a character area, in which a character is displayed, from the name card image under the control of the controlling unit 100.
  • the field candidate area extracting unit 370 extracts a candidate area for a field of which character information is desired to be extracted according to priority. As a result, a time for recognizing characters of the name card can be reduced.
  • the field candidate area extracting unit 370 extracts a candidate area for a field of which character information is desired to be extracted according to priority.
  • the field candidate area extracting unit 370 extracts a field candidate area in association with the determined information for setting extraction field by using a character feature for each field of the name card.
  • the character feature for each field is stored in the storage unit 330.
  • fields of the name card include the company logo field 41, the company name field 42, the department/title field 43, the name field 44, and the detailed information field.
  • the detailed information field may include the zip code field 45, the address field 46, the phone number field 47, the fax number field 48, the cell phone number field 49, the e-mail address field 50, and a homepage address field.
  • the controlling unit 100 may check the field candidate area extracted by the field candidate area extracting unit 370 so as to control the character information extracting unit 390 to extract character information on a candidate area according to the checking result. Furthermore, the controlling unit 100 may receive a user command for checking the field candidate area extracted by the field candidate area extracting unit 370 so as to control the character information extracting unit 390 to extract character information on a lastly selected field.
  • the character information extracting unit 390 extracts character information displayed in the field candidate area extracted by the field candidate area extracting unit 370 under the control of the controlling unit 100 by using a character recognition function.
  • the character information extracting unit 390 extracts the character information by applying a character recognition algorithm to a corresponding field candidate area in association with character features (Korean characters, English characters, and numerals) which are expected to be recorded in each field candidate area.
  • the character information extracting unit 390 extracts the character information by using a Korean recognition algorithm.
  • the extracted field candidate area corresponds to a field composed of English characters and numerals (for example, a phone number, an e-mail, and a homepage address)
  • the character information extracting unit 390 extracts the character information by using an English/numeral recognition algorithm.
  • the controlling unit 100 allows name card information to be displayed on the screen by integrating character information extracted from each field by the character information extracting unit 390 and allows the storage unit 330 to store the name card information in response to a store command.
  • a character area is extracted from a captured name card image, a candidate area for a field containing information to be extracted is extracted, and character information regarding on the extracted candidate area is extracted, thereby obtaining name card information. Therefore, the name card information can be further rapidly and accurately obtained from the name card by using character recognition.
  • a field candidate is estimated of which character information is desired to be extracted from the character area of the name card according to the character feature for each field. Therefore, name card information can be further accurately obtained from the name card by using character recognition.
  • an extraction field is predetermined of which character information is desired to be extracted from a name card, and character information is extracted only for an extracted candidate area by extracting only a candidate area for a field of which character information is desired to be extracted on the basis of setting information.
  • FIG. 5 is a flowchart illustrating a method of rapidly and accurately recognizing a name card by using a portable terminal having a camera according to an embodiment of the present invention.
  • a name card image is captured by using the camera unit 120 so as to read a name card image under the control of the controlling unit 100 (step Sl 10).
  • the controlling unit 100 controls the image processing unit 140 so that a noise image is removed from the read name card image, and image processing suitable for character recognition can be performed (step S 120).
  • the controlling unit 100 allows the display unit 160 to display the name card image that has undergone image processing. Accordingly, character information regarding on a corresponding field is extracted from the name card image, and the extracted information is integrated to generate name card information. This process is displayed on the screen of the display unit 160.
  • the controlling unit 100 controls the character area extracting unit 350 to extract a character area of the character image that has undergone image processing (step S 130).
  • the controlling unit 100 controls the field candidate area extracting unit 370 so that candidate areas for respective fields are sequentially extracted from the extracted character area according to priority, wherein a character to be extracted according to the determined information for setting extraction field is displayed in the candidate areas for respective fields (step S 140).
  • the field candidate area extracting unit 370 extracts the candidate areas for respective fields by using field arrangement pattern information or a displayed character feature for each field.
  • the controlling unit 100 determines a final field area where character information is obtained from the candidate area. Further, the controlling unit 100 controls the character information extracting unit 390 to extract the character information (at least one of Korean characters, English characters, and numerals) by using a corresponding character recognition algorithm (at least one of algorithms for Korean characters, English characters, and numerals).
  • the character information extracting unit 390 uses a Korean character recognition algorithm first to recognize the character recorded in the field candidate area and then extracts character information. Likewise, if the extracted field candidate area is expected to be recorded in English characters or numerals, the character information extracting unit 390 uses an English character or numeral recognition algorithm first to recognize the character recorded in the field candidate area and then extracts character information.
  • the controlling unit 100 integrates character information extracted from each field area by the character information extracting unit 390 to generate a piece of name card information (step S 160).
  • the controlling unit 100 arranges the integrated name card information in a corresponding location according to each field and then displays the information on the screen (step S 170).
  • the controlling unit 100 stores the displayed name card information in the storage unit 330.
  • the controlling unit 100 can edit the name card information according to the input command.
  • a character area is extracted from a captured name card image, and a candidate area for a field containing information to be extracted is extracted by using field arrangement pattern information or field character feature information. Thereafter, character information is extracted by using a character recognition algorithm in association with a feature of characters recorded in the extracted area for the field, thereby finally obtaining name card information. Accordingly, the name card information can be further rapidly and accurately obtained from the name card by using character recognition.
  • FIG. 6 is a flowchart illustrating the step of extracting field candidate areas of FIG.
  • FIGS. 7 to 15 illustrate various examples of an actual name card to which exemplary embodiments of the present invention can be applied.
  • FIG. 6 will be described after arrangement of main information in an actual name card is described in brief with reference to FIGS. 7 to 15.
  • FIGS. 7 to 9 illustrate examples of a name card according to features of a line alignment method. Specifically, a name field and main information fields are left aligned in FIG. 7, center aligned in FIG. 8, and right aligned in FIG. 9.
  • the storage unit 33 stores arrangement pattern information containing the features of the line alignment method of a name card and features of the name field and the main information fields displayed according to the line alignment features.
  • FIG. 10 to 15 illustrate examples of a name card according to features of a line arrangement method. Specifically, a name field and main information fields are vertically arranged in FIGS. 10 to 12, and horizontally arranged in FIGS. 13 to 15.
  • the storage unit 33 stores arrangement pattern information containing the features of the line arrangement method of a name card and features of the name field and the main information fields displayed according to the line arrangement features.
  • the field candidate area extracting unit 370 may use the aforementioned field arrangement pattern information of a name card stored in the storage unit 330 to facilitate the extraction of a field area where information to be extracted is recorded.
  • step S 140 of extracting a field candidate area according to the first embodiment of the present invention will now be described with reference to FIG. 6.
  • the method of FIG. 6 is used when a field candidate area cannot be extracted by using the field arrangement pattern information.
  • the controlling unit 100 controls the field candidate area extracting unit 370 to extract the field candidate area.
  • the process of extracting the field candidate area by the field candidate area extracting unit 370 under the control of the controlling unit 100 will now be described.
  • the field candidate area extracting unit 370 divides a block of each character area in consideration of line space between characters, the height of each line, and a character arrangement method for the extracted character area (step S610).
  • the field candidate area extracting unit 370 checks a line feature for each divided block (step S630). For example, space between lines of a block containing a phone number, an address, a fax number, a mobile phone number, and an e-mail address is narrower than space between lines of other blocks. Further, this block may have the greatest number of lines or may have the horizontally longest line. A feature for each line is checked by the field candidate area extracting unit 370.
  • the field candidate area extracting unit 370 estimates a field type according to the checked feature for each line (step S650). For example, the field candidate area extracting unit 370 may regard a horizontally longest line as an address field.
  • the field candidate area extracting unit 370 checks a character feature of a corresponding field (step S670).
  • a Korean name field is generally distinguished from other fields in terms of a line space, a position, a font size, and a character space. Therefore, in the present invention, a feature of a field may be checked according to the following features of the Korean name field.
  • the height of a name field area is relatively greater than those of other information field areas, and a space between characters is relatively wide and uniform.
  • the name field area includes two to four characters with a uniform interval.
  • the name may present together with a job title and a department instead of being independently present. In this case, character candidate areas in the same field area have different heights from one another. In general, the height of the character area of the job title or department is less than that of the name character area.
  • the name field may be present above or blow the character area of the job title or the department having a relatively low height.
  • Information which can be used for field identification such as a keyword or a character configuration identified for each field, exists after a detailed information field (e.g., a phone number, a fax number, a mobile phone number, an e-mail address, etc.) is recognized.
  • a detailed information field e.g., a phone number, a fax number, a mobile phone number, an e-mail address, etc.
  • a distinguishable feature that can be used for virtually recognizing fields is difficult to be found prior to the recognition.
  • such fields are generally gathered to form a line block.
  • a block area includes the greatest number of lines.
  • the block includes a horizontally longest line which is selected from lines of a name card, for example, an address line or a line in which a phone number, a mobile phone number, and a fax number are sequentially arranged.
  • more character areas are present than other areas.
  • the field candidate area extracting unit 370 determines a field candidate area where information to be recognized is expected to be present (step S690).
  • FIG. 16 is a flowchart illustrating an example of extracting a candidate area for each field (step S 140) of FIG. 5 according to the first embodiment of the present invention.
  • the field candidate area extracting unit 370 extracts an initially recognized area in an uppermost center portion of a name card image as a candidate area for a company name field (step S 141).
  • the field candidate area extracting unit 370 extracts an area which is located below the candidate area for the company name field and is recorded with small characters divided by "/" as a candidate area for a department/title field (step S 142). However, a blank may be used instead of "/" for dividing the department/title field.
  • the field candidate area extracting unit 370 may extract an area which is located below the candidate area for the company name field and is recorded with small characters divided by a blank as the candidate area for the department/title field. [95] The field candidate area extracting unit 370 extracts an area which is located below or a right side of the candidate area for the department/title field and in which large characters are located in the center portion of the name card with a specific interval one by one as a candidate area for a name field (step S 143). [96] The field candidate area extracting unit 370 extracts a paragraph area which is located below the candidate area for the name field and is grouped with small characters as a candidate area for a detailed information field. [97] Specifically, the field candidate area extracting unit 370 extracts an area in which a couple of three numerals are divided by "-" as a candidate area for a zip code field
  • step S 144 The field candidate area extracting unit 370 extracts an area which is located next to the candidate area for the zip code filed and starts with a city name of a province name as a candidate area for an address field (step S 145). [99] The field candidate area extracting unit 370 extracts a numeral area which is located below the candidate area for the address field and starts with a country or local code as a candidate area for a phone number field (step S 146). [100] The field candidate area extracting unit 370 extracts a numeral area which is located below or a side of the candidate area for the phone number field and starts with the same country or local code with the candidate area for the phone number field as a candidate area for a fax number field (step S 147).
  • the field candidate area extracting unit 370 extracts a numeral area which is located below the candidate area for the fax number field and starts with numbers designated to a mobile communication provider as a candidate area for a cell phone number filed (step S 148).
  • the field candidate area extracting unit 370 extracts an area which is located below the candidate area for the cell phone number filed and is displayed with English characters and a special character " @ " as a candidate area for an e-mail address field (step S 149).
  • the field candidate area extracting unit 370 extracts an area displayed with characters including "http” or "www” as a candidate area for a homepage address field.
  • the storage unit 330 stores information for determining a display area and a candidate area for a field corresponding to the display area on the basis of character features of a name card image according to the aforementioned field features.

Abstract

Provided is a portable terminal for recognizing a name card by using an embedded camera and a method thereof. The method includes: a) determining a character feature for each field of the name card; b) extracting a character area from a name card image captured by using the camera when in a name card recognition mode; c) extracting a candidate area for each field, which is estimated to contain information on a field to be extracted from the name card image, by using the character feature for each field; d) extracting character information of each field candidate having a top priority from the candidate area for each field; and e) integrating each extracted character information.

Description

Description
PORTABLE TERMINAL HAVING CAMERA FOR RECOGNIZING NAME CARD AND METHOD THEREOF
USING THE SAME
Technical Field
[1] The present invention relates to a method and apparatus for recognizing a name card by using a portable terminal having a camera, and more particularly, to a method and apparatus for recognizing a name card, wherein character data can be obtained by further rapidly extracting only necessary information after a name card image is captured by using a camera. Background Art
[2] In general, when a user of a portable terminal receives a name card of a counterpart, the user directly inputs and stores necessary content of the name card through a key pad by using a menu of the portable terminal for editing a phone number.
[3] However, the user has to manually perform a lot of operations to manage such personal information. Furthermore, when the user manually arranges many name cards received from his or her acquaintances, it is not easy to manage input data accurately.
[4] In order to solve this disadvantage, a method of storing a name card in a portable terminal has been proposed wherein a name card image is captured by using a camera embedded in the portable terminal, and the captured name card image undergoes character recognition by using a character recognition algorithm.
[5] The character recognition is a technique in which characters recorded in an area having a specific surface such as paper are read and recognized by using a mechanical device, and the characters are converted into a code recognizable by a computer.
[6] A character recognition system generally includes a photoelectric converter, a recognition processor, a memory, and an output unit. The photoelectric converter converts a character recorded on the paper into a voltage waveform. The character recorded on the paper having a shape of a two-dimensional figure is converted into a one-dimensional signal, for example, by a scan method of a television set, which is a time-series change of a voltage waveform. The memory stores an arithmetic control program which controls the recognition processor and data through which the recognized shape is presented in a specific format. The recognition processor processes an unknown character input through the photoelectric converter under the control of the program stored in the memory and compares the processed character with a standard pattern stored in the same memory, so that a character type of a character whose pattern is the most similar to the standard pattern can be recognized as a character type of the unknown character. The output unit sends the recognized character to the computer or other information processors in a suitable manner.
[7] Examples of the character recognition system include: an optical character reader
(OCR) which can recognize both a printed character and a handwritten character; a tablet which can recognize a handwritten character; an optical mark reader (OMR) which can recognize a special character; a bar code; and a magnetic ink character reader (MICR).
[8] FIG. 1 shows an example of a general portable terminal having a camera for recognizing a name card.
[9] As shown in the figure, in the portable terminal, a camera 10 captures a name card image by means of control keys 32 and 34 included in a key pad, and the captured name card image is displayed on a screen 20. The portable terminal recognizes a character from the displayed image by using a character recognition function and then extracts corresponding information. The extracted information is stored as name card data. According to this function, the user can store name card information further con veniently.
[10] FIG. 2 is a flowchart illustrating an example of a conventional method of recognizing a name card by using a portable terminal having a camera.
[11] First, the portable terminal captures a name card image by using the camera 10 and reads the name card image (step SI l). The portable terminal performs image processing for the read name card image. The image processing is equivalent to a step in which the captured name card image is transformed to be easily recognized. The examples of the image processing include binarization and noise removal.
[12] The portable terminal extracts a character area from the name card image that has undergone the image processing (step S 15). The portable terminal performs character recognition for the extracted character area (step S 17). The portable terminal extracts each field information by using the character recognition with respect to all character areas (step S 18). The portable terminal displays the lastly extracted information on the screen 20 (step S 19).
[13] In the conventional method of recognizing a name card by using a portable terminal, a general character recognition method is used when a character in a character area of the name card image is recognized. As a result, in the conventional method of recognizing a name card, in addition to information to be extracted from the name card, character recognition is carried out for all character areas of the name card image that includes even unnecessary information. Therefore, there has been a problem in that a lot of time is required to recognize a character and to extract the name card information.
[14] Furthermore, although a character recognition speed is not a matter in a general personal computer (PC) having a fast processor speed, when the conventional method is used in the portable terminal for name card recognition, the name card is recognized in a slow speed, thereby causing inconvenience in use. Therefore, there has been a problem in that the function for recognizing the name card cannot be widely used.
[15] In addition, in the conventional method of recognizing a name card, character recognition is performed for the whole part of the name card image irrespective of a field type, and then character data is collectively displayed according to the result of recognition. Therefore, the character recognition may be falsely carried out. Disclosure of Invention Technical Problem
[16] The present invention provides a portable terminal that can further rapidly recognize a name card by using an embedded camera and a method thereof.
[17] The present invention also provides a portable terminal that can further accurately recognize a name card according to a field type by using an embedded camera and a method thereof. Technical Solution
[18] According to an aspect of the present invention, there is provided a method of recognizing a name card by using a portable terminal having a camera, the method comprising steps of: a) determining a character feature for each field of the name card; b) extracting a character area from a name card image captured by using the camera when in a name card recognition mode; c) extracting a candidate area for each field, which is estimated to contain information on a field to be extracted from the name card image, by using the character feature for each field; d) extracting character information of each field from the candidate area for each field according to priority of the candidate area for each field; and e) integrating each character information extracted by performing the steps c) and d) with respect to each field included in the name card.
[19] In the aforementioned aspect of the present invention, the method may further comprise steps of: displaying name card data constructed with the integrated character information on a screen; and displaying the name card data modified when a command is input for modifying the displayed name card data.
[20] In addition, the method may further comprise a step of storing the name card data constructed with the integrated character information and the modified name card data according to a store command.
[21] In addition, the method may further comprise a step of determining an extraction field so that a field containing information to be obtained can be determined from all fields of the name card after the step of a), and in the step c), a candidate area for a field corresponding to the determined extraction field is extracted from the name card image by using the character feature for each field.
[22] In addition, the fields of the name card may comprise at least one of a company logo field, a company name field, a department/title field, a name filed, and a detailed information field, and the detailed information field comprises at least one of a zip code field, an address field, a phone number filed, a fax number field, a cell phone number field, a homepage address field, and an e-mail address field.
[23] In addition, in the character feature for each field, the company logo field may be located at the leftmost upper portion of the name card image, the company name field is located at the uppermost center portion of the name card image, the department/title field is located below the company name field and is displayed in small font characters divided by "/" or blank, the name field is located below or a right side of the department/title field and in which large characters are located in the center portion of the name card with a specific interval one by one, and a paragraph area is located below the name field and is grouped with small characters as a candidate area for a detailed information field.
[24] In addition, in the character feature for each field, the detailed information field may comprise the zip code filed which is located such that a couple of three numerals are divided by "-", the address field which is located next to the zip code field and starts with a city name or a province name, the phone number field which is located below the address field and starts with a country code and a local code, the fax number field which is located below or a side of the phone number field and starts with the same country or local code with the phone number field, the cell phone number field which is located below the fax number field and starts with numbers designated to a mobile communication provider, the home page field which is displayed with characters including "http" or "www", and the e-mail address filed which is displayed with English characters and a special character "@".
[25] According to another aspect of the present invention, there is provided a portable terminal for recognizing a name card by using an embedded camera, comprising: a storage unit which stores a program used to recognize the name card and setting information on a character feature for each field of the name card; a character area extracting unit which extracts a character area from a name card image captured by using the camera when in a name card recognition mode; a field candidate area extracting unit which extracts a candidate area for each field, which is estimated to contain information on a field to be extracted from the name card image, by using the character feature for each field; a character information extracting unit which extracts character information of each field from the candidate area for each field according to priority of the candidate area for each field; and a controlling unit which integrates each character information extracted from each field and stores the integration result in the storage unit as name card data.
[26] In the aforementioned aspect of the present invention, the controlling unit may determine an extraction field containing information to be obtained from all fields of the name card according to the input command, and wherein the field candidate area extracting unit extracts a candidate area for a field corresponding to the determined extraction field from the name card image by using the character feature for each field.
[27] In addition, the controlling unit may display the integrated name card data on a screen, and the controlling unit displays the name card data modified when a command is input for modifying the displayed name card data.
[28] According to still another aspect of the present invention, there is provided a method of recognizing a name card by using a portable terminal having a camera, the method comprising steps of: determining a character arrangement pattern for each field of the name card; extracting a character area from a name card image captured by using the camera when in a name card recognition mode; extracting a candidate area for each field, which is estimated to contain information on a field to be extracted from the name card image, by using information on the character arrangement pattern for each field; extracting character information by using a recognizable character recognition algorithm according to a feature of each character displayed in the extracted candidate area for each field; and integrating each extracted character information.
[29] In the aforementioned aspect of the present invention, in the step of extracting character information, when the extracted field candidate area is a character area in which Korean characters are expected to be displayed, the Korean characters may be recognized and extracted from the extracted field candidate area by using a Korean recognition algorithm. Further, in the step of extracting character information, when the extracted field candidate area is a character area in which English/numeral characters are expected to be displayed, the English/numeral characters may be recognized and extracted from the extracted field candidate area by using a English/ numeral recognition algorithm.
[30] In addition, the step of extracting candidate area for each field may comprise steps of: dividing blocks for respective character areas with respect to the extracted character area in consideration of a line space, a height of each line, and a character string arrangement method; checking a line feature for each divided block; estimating a field type according to the checked line feature; checking a character feature with respect to the each estimated field; and determining the candidate area for each field according to the character feature.
[31] In addition, the fields of the name card may comprise at least one of a company logo field, a company name field, a department/title field, a name filed, and a detailed information field. Further, the detailed information field may comprise at least one of a zip code field, an address field, a phone number filed, a fax number field, a cell phone number field, a homepage address field, and an e-mail address field.
Advantageous Effects
[32] According to the present invention, a character area is extracted from a captured name card image, a candidate area for a field containing information to be extracted is extracted by using predetermined field arrangement pattern information or character feature information for each field, and character information regarding on the extracted candidate area is extracted, thereby obtaining name card information. Therefore, the name card information can be further rapidly and accurately obtained from the name card by using character recognition.
[33] In addition, a field candidate is estimated of which character information is desired to be extracted from the character area of the name card according to the character feature for each field. Therefore, name card information can be further accurately obtained from the name card by using character recognition.
[34] In addition, an extraction field is predetermined of which character information is desired to be extracted from a name card, and character information is extracted only for an extracted candidate area by extracting only a candidate area for a field of which character information is desired to be extracted on the basis of setting information. Brief Description of the Drawings
[35] FIG. 1 shows an example of a general portable terminal having a camera for recognizing a name card.
[36] FIG. 2 is a flowchart illustrating an example of a conventional method of recognizing a name card by using a portable terminal having a camera.
[37] FIG.3 shows a general field structure of a name card according to an embodiment of the present invention.
[38] FIG. 4 is a block diagram illustrating a portable terminal for rapidly and accurately recognizing a name card by using an embedded camera according to an embodiment of the present invention.
[39] FIG. 5 is a flowchart illustrating a method of rapidly and accurately recognizing a name card by using a portable terminal having a camera according to an embodiment of the present invention.
[40] FIG. 6 is a flowchart illustrating a step of extracting field candidate areas of FIG. 5 according to a first embodiment of the present invention.
[41] FIGS. 7 to 15 illustrate various examples of an actual name card to which exemplary embodiments of the present invention can be applied.
[42] FIG. 16 is a flowchart illustrating an example of extracting a candidate area for each field (step S 140) of FIG. 5 according to the first embodiment of the present invention. Best Mode for Carrying Out the Invention
[43] Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Throughout the drawings, like reference numerals denote like elements. Descriptions of well-known functions and constructions not directly related to the present invention will be omitted.
[44] FIG.3 shows a general field structure of a name card according to an embodiment of the present invention.
[45] Referring to the figure, the name card includes a company logo field 41 located at the upper leftmost portion of the name card, a company name field 42 located at the right side of the company logo field 41 and at the uppermost portion of the name card, a name field 44 located centrally below the company name field 42 and displayed in larger and thicker characters than other surrounding characters, a department/title field 43 located at the left or right side of the name field 44, and a detailed information field located below the name field 44 and forming one paragraph with small characters.
[46] The detailed information field comprises: a zip code field 45 in which a couple of three numeral characters are divided by "-", an address field 46 which starts with a city name or a province name; a phone number field 47 which starts with a local code; a fax number field 48 located below the phone number field 47, a cell phone number field 49 which starts with numbers designated to a mobile communication provider, and an e-mail address field 50 which includes "@" and English characters.
[47] In this embodiment of the present invention, instead of performing character recognition for the whole part of the name card image, the character area is divided according to a field type in order to achieve fast and accurate character recognition.
[48] FIG. 4 is a block diagram illustrating a portable terminal for rapidly and accurately recognizing a name card by using an embedded camera according to an embodiment of the present invention.
[49] Referring to the figure, the portable terminal includes a controlling unit 100, a camera unit 120, an image processing unit 140, a display unit 160, a wireless communication unit 220, a data processing unit 240, an audio processing unit 260, a key input unit 310, a storage unit 330, a character area extracting unit 350, a field candidate area extracting unit 370, and a character information extracting unit 390.
[50] The controlling unit 100 controls general operations of the portable terminal. Under the control of the controlling unit 100, information is extracted through character recognition for each field of the name card image according to the embodiment of the present invention. Furthermore, under the control of the controlling unit 100, information is extracted through character recognition with respect to each field of the name card image determined by a user.
[51] The camera unit 120 captures an image through a lens. The camera unit 120 includes a camera sensor which converts a captured optical signal into an electrical signal, and a signal processor which converts an analog image signal captured from the camera sensor into digital data. In general, the camera sensor is a charge coupled device (CCD) sensor. The signal process may be a digital signal processor (DSP). In addition, the camera sensor and the signal processor may be implemented in a separation or integration manner. In the embodiment of the present invention, the camera unit 120 captures the name card image according to an input command for image capture and outputs data of the captured image of the name card to the image processing unit 140.
[52] The image processing unit 140 converts the data of the name card image output from the camera unit 120 into screen data to be displayed. The image processing unit 140 removes noise from the data of the name card image output from the camera unit 120 and outputs the resultant data by converting its size according to a feature and size of the display unit 160. Furthermore, the image processing unit 140 includes an image codec to compress data of a frame image displayed in the display unit 160 by using a predetermined method or to restore the compressed data of the frame image into data of an original frame image. The image codec may be a JPEG codec, an MPEG codec, or a wavelet codec. The image processing unit 140 may provide an on screen display (OSD) function. In this case, the image processing unit 140 may allow display data to be displayed in a specific area of a screen under the control of the controlling unit 100.
[53] The display unit 160 displays the name card image output from the image processing unit 140 and displays the display data output from the controlling unit 100 on the screen. The display unit 160 may be a liquid crystal display (LCD). In this case, the display unit 160 may include an LCD controller, a memory capable of storing image data, and an LCD display element. When the LCD is implemented using a touch screen scheme, the LCD may operate as an input unit. Furthermore, the display unit 160 may display name card information on the screen for each field, wherein the name card information has a text format in which the name card image is converted under the control of the controlling unit 100.
[54] The wireless communication unit 220 transmits/receives data for wireless communication of the portable terminal. The wireless communication unit 220 includes an RF transmitter which up-converts and amplifies a frequency of a transmission signal and an RF receiver which amplifies a received signal to have a low noise and down- converts its frequency. The wireless communication unit 220 converts an input signal to be transmitted into a wireless signal and then transmits the resultant signal through a wireless channel. Furthermore, the wireless communication unit 220 receives the wireless signal received through the wireless channel and converts the received signal into data to be output.
[55] The data processing unit 240 includes a transmission module which codes and modulates the signal to be transmitted through the wireless channel and a receiving module which demodulates and decodes the signal received through the wireless channel.
[56] The audio processing unit 260 may be constructed with a codec. The codec includes a data codec which processes packet data and an audio codec which processes an audio (e.g., voice) signal. The audio processing unit 260 converts a digital audio signal received to the data processing unit 240 into an analog signal through the audio codec, so that the converted signal is reproduced through a speaker. Furthermore, the audio processing unit 260 converts an analog audio signal input from a microphone into a digital audio signal through the audio codec, so that the converted signal is output to the data processing unit 240. The codec may be separately provided. Alternatively, the codec may be embedded in the controlling unit 100. In the present embodiment, the audio processing unit 260 may audio-converts each field information extracted according to the name card image under the control of the controlling unit 100 so that the converted information can be output through the speaker.
[57] The key input unit 310 includes a plurality of keys for inputting numeral/character information and a plurality of control keys for controlling operations of the portable terminal. In the present embodiment, the key input unit 310 includes a plurality of keys for controlling the capture of the name card image and the extraction of character information for each field for captured name card image. The key input unit 310 outputs an input command signal to the controlling unit 100.
[58] The storage unit 330 may include a program storage unit and a data storage unit.
The program storage unit may include programs for controlling general operations of the portable terminal and programs required for character recognition in order to extract text information from a character image displayed in a specific area according to the present embodiment. The data storage unit is used to temporarily store data produced while executing the programs. According to the present embodiment, the storage unit 330 stores information for setting extraction field, by which a field of information desired to be obtained from the name card is set, and each field information extracted from the name card image. Furthermore, the storage unit 330 stores field arrangement pattern information determined by analyzing a general type of name cards.
[59] The character area extracting unit 350 extracts a character area, in which a character is displayed, from the name card image under the control of the controlling unit 100.
[60] In a first embodiment of the present invention, by using the field arrangement pattern information stored in the storage unit 330, the field candidate area extracting unit 370 extracts a candidate area for a field of which character information is desired to be extracted according to priority. As a result, a time for recognizing characters of the name card can be reduced.
[61] In a second embodiment of the present invention, on the basis of the determined information for setting extraction field, the field candidate area extracting unit 370 extracts a candidate area for a field of which character information is desired to be extracted according to priority. The field candidate area extracting unit 370 extracts a field candidate area in association with the determined information for setting extraction field by using a character feature for each field of the name card. In this case, the character feature for each field is stored in the storage unit 330.
[62] As shown in FIG. 3, fields of the name card include the company logo field 41, the company name field 42, the department/title field 43, the name field 44, and the detailed information field. The detailed information field may include the zip code field 45, the address field 46, the phone number field 47, the fax number field 48, the cell phone number field 49, the e-mail address field 50, and a homepage address field.
[63] A detailed example of extracting a field candidate area containing character information to be extracted by the field candidate area extracting unit 370 will be described with reference to FIGS. 6 to 16.
[64] The controlling unit 100 may check the field candidate area extracted by the field candidate area extracting unit 370 so as to control the character information extracting unit 390 to extract character information on a candidate area according to the checking result. Furthermore, the controlling unit 100 may receive a user command for checking the field candidate area extracted by the field candidate area extracting unit 370 so as to control the character information extracting unit 390 to extract character information on a lastly selected field.
[65] The character information extracting unit 390 extracts character information displayed in the field candidate area extracted by the field candidate area extracting unit 370 under the control of the controlling unit 100 by using a character recognition function. Preferably, when character information on the extracted field candidate area is extracted, the character information extracting unit 390 extracts the character information by applying a character recognition algorithm to a corresponding field candidate area in association with character features (Korean characters, English characters, and numerals) which are expected to be recorded in each field candidate area.
[66] For example, when the extracted field candidate area corresponds to a Korean character field (for example, a candidate area which is regarded as a name field in the case of a Korean name card), the character information extracting unit 390 extracts the character information by using a Korean recognition algorithm. On the other hand, when the extracted field candidate area corresponds to a field composed of English characters and numerals (for example, a phone number, an e-mail, and a homepage address), the character information extracting unit 390 extracts the character information by using an English/numeral recognition algorithm.
[67] Accordingly, a field area irrelevant to information to be extracted can be prevented from being recognized. Furthermore, with regard to a corresponding field area, a recognition algorithm for a character pattern expected to be recorded in the corresponding field area is first applied. As a result, it is possible to reduce a time for recognizing necessary information.
[68] The controlling unit 100 allows name card information to be displayed on the screen by integrating character information extracted from each field by the character information extracting unit 390 and allows the storage unit 330 to store the name card information in response to a store command.
[69] Accordingly, a character area is extracted from a captured name card image, a candidate area for a field containing information to be extracted is extracted, and character information regarding on the extracted candidate area is extracted, thereby obtaining name card information. Therefore, the name card information can be further rapidly and accurately obtained from the name card by using character recognition. In addition, a field candidate is estimated of which character information is desired to be extracted from the character area of the name card according to the character feature for each field. Therefore, name card information can be further accurately obtained from the name card by using character recognition. In addition, an extraction field is predetermined of which character information is desired to be extracted from a name card, and character information is extracted only for an extracted candidate area by extracting only a candidate area for a field of which character information is desired to be extracted on the basis of setting information.
[70] FIG. 5 is a flowchart illustrating a method of rapidly and accurately recognizing a name card by using a portable terminal having a camera according to an embodiment of the present invention.
[71] First, when a command for recognizing a name card is received through the key input unit 310, a name card image is captured by using the camera unit 120 so as to read a name card image under the control of the controlling unit 100 (step Sl 10). The controlling unit 100 controls the image processing unit 140 so that a noise image is removed from the read name card image, and image processing suitable for character recognition can be performed (step S 120). The controlling unit 100 allows the display unit 160 to display the name card image that has undergone image processing. Accordingly, character information regarding on a corresponding field is extracted from the name card image, and the extracted information is integrated to generate name card information. This process is displayed on the screen of the display unit 160.
[72] The controlling unit 100 controls the character area extracting unit 350 to extract a character area of the character image that has undergone image processing (step S 130). When the character area is extracted, the controlling unit 100 controls the field candidate area extracting unit 370 so that candidate areas for respective fields are sequentially extracted from the extracted character area according to priority, wherein a character to be extracted according to the determined information for setting extraction field is displayed in the candidate areas for respective fields (step S 140). In this case, the field candidate area extracting unit 370 extracts the candidate areas for respective fields by using field arrangement pattern information or a displayed character feature for each field.
[73] When the candidate areas for respective fields are extracted, the controlling unit 100 determines a final field area where character information is obtained from the candidate area. Further, the controlling unit 100 controls the character information extracting unit 390 to extract the character information (at least one of Korean characters, English characters, and numerals) by using a corresponding character recognition algorithm (at least one of algorithms for Korean characters, English characters, and numerals).
[74] In this case, if the extracted field candidate area is expected to be recorded in
Korean characters, the character information extracting unit 390 uses a Korean character recognition algorithm first to recognize the character recorded in the field candidate area and then extracts character information. Likewise, if the extracted field candidate area is expected to be recorded in English characters or numerals, the character information extracting unit 390 uses an English character or numeral recognition algorithm first to recognize the character recorded in the field candidate area and then extracts character information.
[75] The controlling unit 100 integrates character information extracted from each field area by the character information extracting unit 390 to generate a piece of name card information (step S 160). The controlling unit 100 arranges the integrated name card information in a corresponding location according to each field and then displays the information on the screen (step S 170). When a store command is received with respect to the displayed name card information, the controlling unit 100 stores the displayed name card information in the storage unit 330. In this case, when an edit command is received with respect to the displayed name card information, the controlling unit 100 can edit the name card information according to the input command.
[76] Therefore, a character area is extracted from a captured name card image, and a candidate area for a field containing information to be extracted is extracted by using field arrangement pattern information or field character feature information. Thereafter, character information is extracted by using a character recognition algorithm in association with a feature of characters recorded in the extracted area for the field, thereby finally obtaining name card information. Accordingly, the name card information can be further rapidly and accurately obtained from the name card by using character recognition.
[77] FIG. 6 is a flowchart illustrating the step of extracting field candidate areas of FIG.
5 according to a first embodiment of the present invention. FIGS. 7 to 15 illustrate various examples of an actual name card to which exemplary embodiments of the present invention can be applied.
[78] FIG. 6 will be described after arrangement of main information in an actual name card is described in brief with reference to FIGS. 7 to 15.
[79] FIGS. 7 to 9 illustrate examples of a name card according to features of a line alignment method. Specifically, a name field and main information fields are left aligned in FIG. 7, center aligned in FIG. 8, and right aligned in FIG. 9. The storage unit 33 stores arrangement pattern information containing the features of the line alignment method of a name card and features of the name field and the main information fields displayed according to the line alignment features.
[80] FIG. 10 to 15 illustrate examples of a name card according to features of a line arrangement method. Specifically, a name field and main information fields are vertically arranged in FIGS. 10 to 12, and horizontally arranged in FIGS. 13 to 15. The storage unit 33 stores arrangement pattern information containing the features of the line arrangement method of a name card and features of the name field and the main information fields displayed according to the line arrangement features.
[81] Accordingly, the field candidate area extracting unit 370 may use the aforementioned field arrangement pattern information of a name card stored in the storage unit 330 to facilitate the extraction of a field area where information to be extracted is recorded.
[82] The step S 140 of extracting a field candidate area according to the first embodiment of the present invention will now be described with reference to FIG. 6. The method of FIG. 6 is used when a field candidate area cannot be extracted by using the field arrangement pattern information.
[83] The controlling unit 100 controls the field candidate area extracting unit 370 to extract the field candidate area. The process of extracting the field candidate area by the field candidate area extracting unit 370 under the control of the controlling unit 100 will now be described.
[84] Referring to FIG. 6, the field candidate area extracting unit 370 divides a block of each character area in consideration of line space between characters, the height of each line, and a character arrangement method for the extracted character area (step S610).
[85] In this case, the field candidate area extracting unit 370 checks a line feature for each divided block (step S630). For example, space between lines of a block containing a phone number, an address, a fax number, a mobile phone number, and an e-mail address is narrower than space between lines of other blocks. Further, this block may have the greatest number of lines or may have the horizontally longest line. A feature for each line is checked by the field candidate area extracting unit 370.
[86] After checking the feature for each line, the field candidate area extracting unit 370 estimates a field type according to the checked feature for each line (step S650). For example, the field candidate area extracting unit 370 may regard a horizontally longest line as an address field.
[87] After estimating the field type, the field candidate area extracting unit 370 checks a character feature of a corresponding field (step S670). For example, a Korean name field is generally distinguished from other fields in terms of a line space, a position, a font size, and a character space. Therefore, in the present invention, a feature of a field may be checked according to the following features of the Korean name field.
[88] First, the height of a name field area is relatively greater than those of other information field areas, and a space between characters is relatively wide and uniform. Second, if a name is independently present, in general, the name field area includes two to four characters with a uniform interval. Third, the name may present together with a job title and a department instead of being independently present. In this case, character candidate areas in the same field area have different heights from one another. In general, the height of the character area of the job title or department is less than that of the name character area. Forth, the name field may be present above or blow the character area of the job title or the department having a relatively low height.
[89] Information, which can be used for field identification such as a keyword or a character configuration identified for each field, exists after a detailed information field (e.g., a phone number, a fax number, a mobile phone number, an e-mail address, etc.) is recognized. However, a distinguishable feature that can be used for virtually recognizing fields is difficult to be found prior to the recognition. However, such fields are generally gathered to form a line block. In the present embodiment, it is possible to decide locations of the fields by using this feature. Examples of features that can be used for finding a line block including detailed information fields will now be described.
[90] First, a block area includes the greatest number of lines. Second, if the first requirement is not satisfied, the block includes a horizontally longest line which is selected from lines of a name card, for example, an address line or a line in which a phone number, a mobile phone number, and a fax number are sequentially arranged. Third, more character areas are present than other areas. [91] According to the feature for each field, the field candidate area extracting unit 370 determines a field candidate area where information to be recognized is expected to be present (step S690). [92] FIG. 16 is a flowchart illustrating an example of extracting a candidate area for each field (step S 140) of FIG. 5 according to the first embodiment of the present invention.
The example of FIG. 16 can be applied when a field candidate area cannot be extracted according to field arrangement pattern information and when a feature of each line is not easily checked. [93] First, the field candidate area extracting unit 370 extracts an initially recognized area in an uppermost center portion of a name card image as a candidate area for a company name field (step S 141). [94] The field candidate area extracting unit 370 extracts an area which is located below the candidate area for the company name field and is recorded with small characters divided by "/" as a candidate area for a department/title field (step S 142). However, a blank may be used instead of "/" for dividing the department/title field. In this case, the field candidate area extracting unit 370 may extract an area which is located below the candidate area for the company name field and is recorded with small characters divided by a blank as the candidate area for the department/title field. [95] The field candidate area extracting unit 370 extracts an area which is located below or a right side of the candidate area for the department/title field and in which large characters are located in the center portion of the name card with a specific interval one by one as a candidate area for a name field (step S 143). [96] The field candidate area extracting unit 370 extracts a paragraph area which is located below the candidate area for the name field and is grouped with small characters as a candidate area for a detailed information field. [97] Specifically, the field candidate area extracting unit 370 extracts an area in which a couple of three numerals are divided by "-" as a candidate area for a zip code field
(step S 144). [98] The field candidate area extracting unit 370 extracts an area which is located next to the candidate area for the zip code filed and starts with a city name of a province name as a candidate area for an address field (step S 145). [99] The field candidate area extracting unit 370 extracts a numeral area which is located below the candidate area for the address field and starts with a country or local code as a candidate area for a phone number field (step S 146). [100] The field candidate area extracting unit 370 extracts a numeral area which is located below or a side of the candidate area for the phone number field and starts with the same country or local code with the candidate area for the phone number field as a candidate area for a fax number field (step S 147).
[101] The field candidate area extracting unit 370 extracts a numeral area which is located below the candidate area for the fax number field and starts with numbers designated to a mobile communication provider as a candidate area for a cell phone number filed (step S 148).
[102] The field candidate area extracting unit 370 extracts an area which is located below the candidate area for the cell phone number filed and is displayed with English characters and a special character " @ " as a candidate area for an e-mail address field (step S 149).
[103] The field candidate area extracting unit 370 extracts an area displayed with characters including "http" or "www" as a candidate area for a homepage address field.
[104] The storage unit 330 stores information for determining a display area and a candidate area for a field corresponding to the display area on the basis of character features of a name card image according to the aforementioned field features.
[105] While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims

Claims
[1] A method of recognizing a name card by using a portable terminal having a camera, the method comprising steps of: a) determining a character feature for each field of the name card; b) extracting a character area from a name card image captured by using the camera when in a name card recognition mode; c) extracting a candidate area for each field, which is estimated to contain information on a field to be extracted from the name card image, by using the character feature for each field; d) extracting character information of each field from the candidate area for each field according to priority of the candidate area for each field; and e) integrating each character information extracted by performing the steps c) and d) with respect to each field included in the name card.
[2] The method of claim 1, further comprising steps of: displaying name card data constructed with the integrated character information on a screen; and displaying the name card data modified when a command is input for modifying the displayed name card data.
[3] The method of claim 1 or 2, further comprising a step of storing the name card data constructed with the integrated character information and the modified name card data according to a store command.
[4] The method of claim 1, further comprising a step of determining an extraction field so that a field containing information to be obtained can be determined from all fields of the name card after the step of a), and in the step c), a candidate area for a field corresponding to the determined extraction field is extracted from the name card image by using the character feature for each field.
[5] The method of claim 1, wherein the fields of the name card comprise at least one of a company logo field, a company name field, a department/title field, a name filed, and a detailed information field, and the detailed information field comprises at least one of a zip code field, an address field, a phone number filed, a fax number field, a cell phone number field, a homepage address field, and an e-mail address field.
[6] The method of claim 5, wherein, in the character feature for each field, the company logo field is located at the leftmost upper portion of the name card image, the company name field is located at the uppermost center portion of the name card image, the department/title field is located below the company name field and is displayed in small font characters divided by "/" or blank, the name field is located below or a right side of the department/title field and in which large characters are located in the center portion of the name card with a specific interval one by one, and a paragraph area is located below the name field and is grouped with small characters as a candidate area for a detailed information field.
[7] The method of claim 6, wherein, in the character feature for each field, the detailed information field comprises the zip code filed which is located such that a couple of three numerals are divided by "-", the address field which is located next to the zip code field and starts with a city name or a province name, the phone number field which is located below the address field and starts with a country code and a local code, the fax number field which is located below or a side of the phone number field and starts with the same country or local code with the phone number field, the cell phone number field which is located below the fax number field and starts with numbers designated to a mobile communication provider, the home page field which is displayed with characters including "http" or "www", and the e-mail address filed which is displayed with English characters and a special character "@".
[8] A portable terminal for recognizing a name card by using an embedded camera, comprising: a storage unit which stores a program used to recognize the name card and setting information on a character feature for each field of the name card; a character area extracting unit which extracts a character area from a name card image captured by using the camera when in a name card recognition mode; a field candidate area extracting unit which extracts a candidate area for each field, which is estimated to contain information on a field to be extracted from the name card image, by using the character feature for each field; a character information extracting unit which extracts character information of each field from the candidate area for each field according to priority of the candidate area for each field; and a controlling unit which integrates each character information extracted from each field and stores the integration result in the storage unit as name card data.
[9] The portable terminal of claim 10, wherein the controlling unit determines an extraction field containing information to be obtained from all fields of the name card according to the input command, and wherein the field candidate area extracting unit extracts a candidate area for a field corresponding to the determined extraction field from the name card image by using the character feature for each field.
[10] The portable terminal of claim 8, wherein the fields of the name card comprise at least one of a company logo field, a company name field, a department/title field, a name filed, and a detailed information field.
[11] The portable terminal of claim 10, wherein the detailed information field comprises at least one of a zip code field, an address field, a phone number filed, a fax number field, a cell phone number field, a homepage address field, and an e-mail address field.
[12] The portable terminal of claim 11, wherein the controlling unit displays the integrated name card data on a screen, and the controlling unit displays the name card data modified when a command is input for modifying the displayed name card data.
[13] A method of recognizing a name card by using a portable terminal having a camera, the method comprising steps of: determining a character arrangement pattern for each field of the name card; extracting a character area from a name card image captured by using the camera when in a name card recognition mode; extracting a candidate area for each field, which is estimated to contain information on a field to be extracted from the name card image, by using information on the character arrangement pattern for each field; extracting character information by using a recognizable character recognition algorithm according to a feature of each character displayed in the extracted candidate area for each field; and integrating each extracted character information.
[14] The method of claim 13, wherein, in the step of extracting character information, when the extracted field candidate area is a character area in which Korean characters are expected to be displayed, the Korean characters are recognized and extracted from the extracted field candidate area by using a Korean recognition algorithm.
[15] The method of claim 13, wherein, in the step of extracting character information, when the extracted field candidate area is a character area in which English/ numeral characters are expected to be displayed, the English/numeral characters are recognized and extracted from the extracted field candidate area by using a English/numeral recognition algorithm.
[16] The method of claim 15, wherein the step of extracting candidate area for each field comprises steps of: dividing blocks for respective character areas with respect to the extracted character area in consideration of a line space, a height of each line, and a character string arrangement method; checking a line feature for each divided block; estimating a field type according to the checked line feature; checking a character feature with respect to the each estimated field; and determining the candidate area for each field according to the character feature. [17] The method of claim 13, wherein the fields of the name card comprise at least one of a company logo field, a company name field, a department/title field, a name filed, and a detailed information field. [18] The method of claim 17, wherein the detailed information field comprises at least one of a zip code field, an address field, a phone number filed, a fax number field, a cell phone number field, a homepage address field, and an e-mail address field.
PCT/KR2007/000158 2006-01-10 2007-01-09 Portable terminal having camera for recognizing name card and method thererof using the same WO2007081147A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2006-0002916 2006-01-10
KR1020060002916A KR100664421B1 (en) 2006-01-10 2006-01-10 Portable terminal and method for recognizing name card using having camera

Publications (1)

Publication Number Publication Date
WO2007081147A1 true WO2007081147A1 (en) 2007-07-19

Family

ID=37866849

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2007/000158 WO2007081147A1 (en) 2006-01-10 2007-01-09 Portable terminal having camera for recognizing name card and method thererof using the same

Country Status (2)

Country Link
KR (1) KR100664421B1 (en)
WO (1) WO2007081147A1 (en)

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8374646B2 (en) 2009-10-05 2013-02-12 Sony Corporation Mobile device visual input system and methods
WO2015160988A1 (en) * 2014-04-15 2015-10-22 Kofax, Inc. Smart optical input/output (i/o) extension for context-dependent workflows
US9342741B2 (en) 2009-02-10 2016-05-17 Kofax, Inc. Systems, methods and computer program products for determining document validity
US9349063B2 (en) 2010-10-22 2016-05-24 Qualcomm Incorporated System and method for capturing token data with a portable computing device
US9349046B2 (en) 2009-02-10 2016-05-24 Kofax, Inc. Smart optical input/output (I/O) extension for context-dependent workflows
US9396388B2 (en) 2009-02-10 2016-07-19 Kofax, Inc. Systems, methods and computer program products for determining document validity
US9576272B2 (en) 2009-02-10 2017-02-21 Kofax, Inc. Systems, methods and computer program products for determining document validity
US9747504B2 (en) 2013-11-15 2017-08-29 Kofax, Inc. Systems and methods for generating composite images of long documents using mobile video data
US9760788B2 (en) 2014-10-30 2017-09-12 Kofax, Inc. Mobile document detection and orientation based on reference object characteristics
US9767354B2 (en) 2009-02-10 2017-09-19 Kofax, Inc. Global geographic information retrieval, validation, and normalization
US9769354B2 (en) 2005-03-24 2017-09-19 Kofax, Inc. Systems and methods of processing scanned data
US9779296B1 (en) 2016-04-01 2017-10-03 Kofax, Inc. Content-based detection and three dimensional geometric reconstruction of objects in image and video data
US9819825B2 (en) 2013-05-03 2017-11-14 Kofax, Inc. Systems and methods for detecting and classifying objects in video captured using mobile devices
US9946954B2 (en) 2013-09-27 2018-04-17 Kofax, Inc. Determining distance between an object and a capture device based on captured image data
US9996741B2 (en) 2013-03-13 2018-06-12 Kofax, Inc. Systems and methods for classifying objects in digital images captured using mobile devices
US10146803B2 (en) 2013-04-23 2018-12-04 Kofax, Inc Smart mobile application development platform
US10146795B2 (en) 2012-01-12 2018-12-04 Kofax, Inc. Systems and methods for mobile image capture and processing
US10242285B2 (en) 2015-07-20 2019-03-26 Kofax, Inc. Iterative recognition-guided thresholding and data extraction
US10467465B2 (en) 2015-07-20 2019-11-05 Kofax, Inc. Range and/or polarity-based thresholding for improved data extraction
US10657600B2 (en) 2012-01-12 2020-05-19 Kofax, Inc. Systems and methods for mobile image capture and processing
US10803350B2 (en) 2017-11-30 2020-10-13 Kofax, Inc. Object detection and image cropping using a multi-detector approach
JP2021504781A (en) * 2017-12-01 2021-02-15 インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Machines Corporation Methods, computer programs and systems for extracting document metadata based on blocks

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101796946B1 (en) * 2017-02-02 2017-11-13 에스비주식회사 Enterprise reputation information service system
KR102134024B1 (en) 2018-12-31 2020-07-15 주식회사 딥비전 Method and Mobile Terminal for Recognizing Name Card
KR102259477B1 (en) 2019-03-22 2021-06-01 엄춘호 Smart information input method and smart information input system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100459074B1 (en) * 2004-08-05 2004-12-03 주식회사 인지소프트 Method for recognizing name card by mobile phone having camera
US20050037806A1 (en) * 2003-08-12 2005-02-17 Kyoung-Weon Na Managing an address book in portable terminal having a camera
JP2005055969A (en) * 2003-08-06 2005-03-03 Hitachi Ltd Portable information terminal

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002152696A (en) 2000-11-10 2002-05-24 Hitachi Ltd Portable terminal
KR100593986B1 (en) * 2002-09-11 2006-07-03 삼성전자주식회사 Device and method for recognizing character image in picture screen
KR101024433B1 (en) * 2003-12-18 2011-03-23 엘지전자 주식회사 Mobile communication terminal and phone number automatic storing method thereof
KR20050077840A (en) * 2004-01-28 2005-08-04 주식회사 팬택앤큐리텔 Method of perceiving images in the mobile communication terminal

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005055969A (en) * 2003-08-06 2005-03-03 Hitachi Ltd Portable information terminal
US20050037806A1 (en) * 2003-08-12 2005-02-17 Kyoung-Weon Na Managing an address book in portable terminal having a camera
KR100459074B1 (en) * 2004-08-05 2004-12-03 주식회사 인지소프트 Method for recognizing name card by mobile phone having camera

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9769354B2 (en) 2005-03-24 2017-09-19 Kofax, Inc. Systems and methods of processing scanned data
US9767354B2 (en) 2009-02-10 2017-09-19 Kofax, Inc. Global geographic information retrieval, validation, and normalization
US9342741B2 (en) 2009-02-10 2016-05-17 Kofax, Inc. Systems, methods and computer program products for determining document validity
US9349046B2 (en) 2009-02-10 2016-05-24 Kofax, Inc. Smart optical input/output (I/O) extension for context-dependent workflows
US9396388B2 (en) 2009-02-10 2016-07-19 Kofax, Inc. Systems, methods and computer program products for determining document validity
US9576272B2 (en) 2009-02-10 2017-02-21 Kofax, Inc. Systems, methods and computer program products for determining document validity
US9747269B2 (en) 2009-02-10 2017-08-29 Kofax, Inc. Smart optical input/output (I/O) extension for context-dependent workflows
US8374646B2 (en) 2009-10-05 2013-02-12 Sony Corporation Mobile device visual input system and methods
US9349063B2 (en) 2010-10-22 2016-05-24 Qualcomm Incorporated System and method for capturing token data with a portable computing device
US10657600B2 (en) 2012-01-12 2020-05-19 Kofax, Inc. Systems and methods for mobile image capture and processing
US10146795B2 (en) 2012-01-12 2018-12-04 Kofax, Inc. Systems and methods for mobile image capture and processing
US10664919B2 (en) 2012-01-12 2020-05-26 Kofax, Inc. Systems and methods for mobile image capture and processing
US9996741B2 (en) 2013-03-13 2018-06-12 Kofax, Inc. Systems and methods for classifying objects in digital images captured using mobile devices
US10127441B2 (en) 2013-03-13 2018-11-13 Kofax, Inc. Systems and methods for classifying objects in digital images captured using mobile devices
US10146803B2 (en) 2013-04-23 2018-12-04 Kofax, Inc Smart mobile application development platform
US9819825B2 (en) 2013-05-03 2017-11-14 Kofax, Inc. Systems and methods for detecting and classifying objects in video captured using mobile devices
US9946954B2 (en) 2013-09-27 2018-04-17 Kofax, Inc. Determining distance between an object and a capture device based on captured image data
US9747504B2 (en) 2013-11-15 2017-08-29 Kofax, Inc. Systems and methods for generating composite images of long documents using mobile video data
CN106170798A (en) * 2014-04-15 2016-11-30 柯法克斯公司 Intelligent optical input/output (I/O) for context-sensitive workflow extends
WO2015160988A1 (en) * 2014-04-15 2015-10-22 Kofax, Inc. Smart optical input/output (i/o) extension for context-dependent workflows
US9760788B2 (en) 2014-10-30 2017-09-12 Kofax, Inc. Mobile document detection and orientation based on reference object characteristics
US10242285B2 (en) 2015-07-20 2019-03-26 Kofax, Inc. Iterative recognition-guided thresholding and data extraction
US10467465B2 (en) 2015-07-20 2019-11-05 Kofax, Inc. Range and/or polarity-based thresholding for improved data extraction
US9779296B1 (en) 2016-04-01 2017-10-03 Kofax, Inc. Content-based detection and three dimensional geometric reconstruction of objects in image and video data
US10803350B2 (en) 2017-11-30 2020-10-13 Kofax, Inc. Object detection and image cropping using a multi-detector approach
US11062176B2 (en) 2017-11-30 2021-07-13 Kofax, Inc. Object detection and image cropping using a multi-detector approach
JP2021504781A (en) * 2017-12-01 2021-02-15 インターナショナル・ビジネス・マシーンズ・コーポレーションInternational Business Machines Corporation Methods, computer programs and systems for extracting document metadata based on blocks
JP7289047B2 (en) 2017-12-01 2023-06-09 インターナショナル・ビジネス・マシーンズ・コーポレーション Method, computer program and system for block-based document metadata extraction

Also Published As

Publication number Publication date
KR100664421B1 (en) 2007-01-03

Similar Documents

Publication Publication Date Title
WO2007081147A1 (en) Portable terminal having camera for recognizing name card and method thererof using the same
US20100268929A1 (en) Electronic device and setting method thereof
US20110157215A1 (en) Image output device, image output system and image output method
KR20060050729A (en) Method and apparatus for processing document image captured by camera
CN107111865A (en) Text based Image Adjusting size
US10126907B2 (en) Emulation of multifunction peripheral via remote control device based on display aspect ratios
KR100547738B1 (en) Apparatus and method for managing address book in portable terminal with camera
CN112232260A (en) Subtitle region identification method, device, equipment and storage medium
WO2006136914A1 (en) Method, electronic device and computer program product for file naming with ocr
KR100736342B1 (en) Portable terminal apparatus and schedule administering method thereof
KR100633231B1 (en) Portable terminal with a information search function based on gesture recognition and implementating method thereof
JPH10289243A (en) Data retrieval system
CN108108646B (en) Bar code information identification method, terminal and computer readable storage medium
JP4983464B2 (en) Form image processing apparatus and form image processing program
JP4800144B2 (en) Character string determination device, character string determination method, character string determination program, and computer-readable recording medium
JP2000032111A (en) Portable information reading processor and control method
US10404870B2 (en) Image processing apparatus, setting-value setting method and computer-readable recording medium recording setting-value setting program
KR100619715B1 (en) Document image photograph method for mobile communication device and word extraction method from the document image
KR101499133B1 (en) Method and device for performing menu in wireless terminal
KR101412953B1 (en) Method for removing the staff lines from a music score image
JP2001008072A (en) Electronic camera and its control method
JP2005044052A (en) Portable character recognition device
JP5271028B2 (en) IC card reader and IC card reading method
KR100656875B1 (en) Method and apparatus for keeping a household account book with a portable terminal
JP2008021173A (en) Personal digital assistant and electronic mail system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 07708455

Country of ref document: EP

Kind code of ref document: A1