WO2001004790A1

WO2001004790A1 - Sign translator

Info

Publication number: WO2001004790A1
Application number: PCT/IL2000/000399
Authority: WO
Inventors: Shlomo Urbach; Jacob Gil
Original assignee: Shlomo Urbach; Jacob Gil
Priority date: 1999-07-08
Filing date: 2000-07-06
Publication date: 2001-01-18
Also published as: AU5703500A; IL130847A0

Abstract

An automatic device, of particular utility for tourists, for capturing an image at a distance and translating text within the image, comprising: (a) photographing means (54) for capturing an image containing a textual image, (b) character recognition means (56) for converting the textual image into correponding text data written in a source language, and (c) translation means (58) for translating the text data from the source language to a target language text.

Description

SIGN TRANSLATOR

FIELD AND BACKGROUND OF THE INVENTION

The present invention relates to a system for automatic translation of

text, and. more particularly, to a system for capturing text from a distance and

automatically providing a text translation into the desired language.

Known in the art are various types of scanners that are capable of

identifying text and translating the text into another language. The input data

scanned are converted into system data and input text data using optical

character recognition (OCR) programs, which are widely available and the

operation of which is well known in the field. OCR programs are often

designed towards scanning and recognizing alphanumeric text. Some OCR

programs are designed towards scanning and recognizing ideographic

characters, such as Japanese kana.

An example of one popular commercial application is Quicktionary™.

a portable, handheld scanner that scans and automatically displays a

translation. The built-in OCR program is capable of reading and identifying

multiple fonts and type sizes. The internal memory contains several hundred

thousand words and idioms.

The scanning translators of the known art operate by pressing the paper

or surface bearing the text (or characters) against the scanning surface of the scanner. In portable scanning translators, the entire scanner is brought near

to the text-bearing surface at which point the scanning is initiated.

Known translation systems are incapable, however, of reading and

translating text or characters from afar. This is a serious disadvantage, as

often the text-bearing surface is not under thumb and may be substantially

inaccessible. For example, millions of tourists each year travel in countries

in which for them, the local alphabet, including traffic signs, street signs,

advertisements, is incomprehensible. Although in theory it is possible to

carry hand-held portable translators and type in the words or sentence that

needs translation, in practice such use is clumsy and time-consuming.

Moreover, hand-held portable translators often do not have the capability of

entering ideographic characters and forms belonging to foreign alphabets

such as Cyrillic or Hebrew. Finally, typographical error or improper

identification of a foreign form or character by the tourist/user are highly

probable, and may often lead to mistranslation or to an inability to provide a

translation.

There is therefore a recognized need for, and it would be highly

advantageous to have, a system that would be capable of reading a

text-bearing and/or character-bearing object from afar and translating the text

and/or characters into the requisite language. It would be of particular

advantage if such an invention would be economical, reliable, and convenient

to use. SUMMARY OF THE INVENTION

The present invention is an automatic device, of particular utility for

tourists, for capturing an image at a distance and translating text within the

image, comprising: (a) photographing means for capturing an image

containing a textual image, (b) character recognition means for converting the

textual image into corresponding text data written in a source language, and

(c) translation means for translating the text data from the source language to a

target language text.

According to further features in the described preferred embodiments,

the target language text is provided as visual text.

According to still further features in the described preferred

embodiments, the visual text is provided on a visual display.

According to still further features in the described preferred

embodiments, the target language text is provided audially.

According to still further features in the described preferred

embodiments, the photographing device is a digital video camera.

According to still further features in the described preferred

embodiments, the photographing device is a digital snapshot (still-photo)

camera.

According to still further features in the described preferred

embodiments, the translation means for translating the text data from the

source language to a target language text is provided by accessing the Internet.

According to still further features in the described preferred embodiments, the accessing of the Internet is performed using a portable

computer.

According to still further features in the described preferred

embodiments, the accessing of the Internet is performed using a Personal

Digital Assistant (PDA).

According to still further features in the described preferred

embodiments, the accessing of the Internet is performed using a mobile phone.

According to still further features in the described preferred

embodiments, the visual display is a visual display of a mobile phone.

According to still further features in the described preferred

embodiments, the automatic device of the present invention further comprises

(d) at least one feature selected from the group consisting of: tour books,

business information, language-learning means, maps, and travel directions.

According to still further features in the described preferred

embodiments, the automatic device of the present invention further comprises

(d) user-identification means.

According to still further features in the described preferred

embodiments, the automatic device of the present invention further comprises

(d) at least one feature selected from the group consisting of: credit cards,

travel tickets, membership cards, car-rental contracts, hotel reservations, and

entertainment tickets.

According to still further features in the described preferred embodiments, the automatic device of the present invention further comprises

(d) an audio device for recording voice data in the source language, and (e)

translation means for translating the voice data from the source language to the

target language text.

According to still further features in the described preferred

embodiments, the target language text is provided on a visual display or

audially.

The present invention successfully addresses the shortcomings of the

existing technologies by providing a device capable of instantly capturing an

image viewed from a distance, identifying the text therein, and translating the

text to the target language.

BRIEF DESCRIPTION OF THE DRAWINGS

The invention is herein described, by way of example only, with

reference to the accompanying drawings. With specific reference now to the

drawings in detail, it is stressed that the particulars shown are by way of

example and for purposes of illustrative discussion of the preferred

embodiments of the present invention only, and are presented in the cause of

providing what is believed to be the most useful and readily understood

description of the principles and conceptual aspects of the invention. In this

regard, no attempt is made to show structural details of the invention in more

detail than is necessary for a fundamental understanding of the invention, the description taken with the drawings making apparent to those skilled in the

art how the several forms of the invention may be embodied in practice.

In the drawings:

FIG. la is a schematic illustration of the exterior of a device according

to the present invention, integrated into a digital video camera.

FIG. lb is a schematic illustration of the inner workings of the device

of FIG. la.

FIG. 2 illustrates the camera display of the system of FIG. 1.

DESCRIPTION OF THE PREFERRED EMBODIMENTS

The present invention is an automatic system that captures text, usually

at a distance, identifies the text and translates the text into the requisite

language.

The principles and operation of the device according to the present

invention may be better understood with reference to the drawings and the

accompanying description.

Before explaining at least one embodiment of the invention in detail, it

is to be understood that the invention is not limited in its application to the

details of construction and the arrangement of the components set forth in the

following description or illustrated in the drawing. The invention is capable

of other embodiments or of being practiced or carried out in various ways.

Also, it is to be understood that the phraseology and terminology employed

herein is for the purpose of description and should not be regarded as

limitinε. Referring now to the drawings, Figure la is a schematic illustration of

the exterior of a device according to the present invention, integrated into a

conventional digital video camera 10. The digital video camera 10 has two

main operating buttons: a first operating button 12 for filming, and a second

operating button 14 for the purpose of the present invention. When the

second operating button 14 is pressed, the text is captured, identified, and

translated into the requisite (target) language.

Figure lb is a schematic illustration of the inner workings of the device

of Figure la, integrated into a conventional digital video camera 10. The lens

50. which represents the optics of the device, focusses a text-containing

image (not shown) on to a CCD (Charge Coupled Device) array 52. The

voltage of each element of the CCD array corresponds to the light intensity

focussed on the element. The image capturing unit 54 reads the voltage of

each element in the array, yielding a field of pixels.

The text within the captured image from the image capturing unit 54 is

passed on to the character recognition unit 56, which identifies the text.

Subsequently, the identified text is passed on to the translating unit 58, which

translates the source text into the target language. The translated (target

language) text is then provided visually on a display 20. Alternatively, the

translated text is passed on to a speech synthesizer 62 which converts the text

into audible speech, which is then presented to the user by means of a speaker

64. It should be emphasized that the system of the present invention can

utilize and integrate existing technologies such as OCR, digital video

equipment, and computerized translators such as Quicktionary™. While

some OCR technologies require that the source language be identified by the

user, others are capable of identifying the source language. The present

invention can utilize both of these OCR technologies, as well as other kinds

of character recognition technologies. In any event, the target language can

be dedicated to a particular target language, loaded as a sole target language

by the user, or loaded as one of several target languages by the user (in

which case, the user must specify which target language is desired). All of

these translating options are possible using translating components of the

prior art.

Figure 2 illustrates the camera display 20 of the system of Figure 1.

Within the camera display 20, a sign 22 having the text 24 "MARKET" is

shown. The sign 22 containing text 24 lies within the field of translation 26.

Upon pressing the "translate" button (the second operating button 14 of

Figure la), the text is translated into the desired target language, in this case,

Hebrew (

). The translated text 28 is then provided at the bottom 30 of

the camera display 20.

In a preferred embodiment, the field of translation 26 is a sub-frame of

the camera display 20, preferably located near the center of the camera

display 20. In another preferred embodiment, the field of translation 26 can

be adjusted according to the size of the text 24. In the figures and accompanying description above, the device

according to the present invention is integrated in a digital camera, such as a

digital video camera or a digital snapshot (still-photo) camera. Thus, the

inventive features are built into the digital camera. In principle, such a

system can include any equipment used to read or obtain visual information

at a distance, e.g., digital binoculars or surveying instruments of various

kinds.

The present invention may also be an add-on unit to an existing digital

camera, i.e., a camera that was manufactured without having the present

invention in mind. In connecting the device to an existing camera unit, a

short cable having an appropriate fitting is used, the fitting being connected

to an IEEE 1394 outlet or similar outlet. Such outlets are typically used

today to connect a digital video camera to a computer. Connection to a

digital camera is typically effected via existing-type communication ports

such as USB.

In add-on systems of this type, wherein the device of the present

invention is hooked up to existing equipment (compatible, but not embedded

or built-in), the inventive device typically includes a display screen,

keyboard (having one or more keys or buttons), and computer

communication cable.

In another kind of add-on unit, the device according to the present

invention, having a dedicated element for capturing images containing text, is added-on to a mobile phone or to a Personal Digital Assistant (PDA) such as

Palm Pilot™.

Alternatively, the present invention may be a stand-alone unit, having a

dedicated element for capturing images containing text instead of being built

into a digital camera.

It must be emphasized that tourists are accustomed to traveling with

cameras of various kinds. Because the device according to the present

invention can be affixed to cameras and the like, and can even be built as an

integral part of the camera, the portable text-capturing and text-translating

device is particularly easy and convenient to use.

The dictionary or dictionaries providing the translation can be stored

physically within the device. In a preferred embodiment, the dictionary or

dictionaries providing the translation can be accessed via the Internet. This is

particularly relevant for applications in which the equipment does not

necessarily have considerable computing power, as with many cellular

phones.

As used herein in the specification and in the claims section that

follows, the term "text" includes sentences, phrases, words, letters and

ideographic signs. The letters include, by way of example, Braille letters,

and the ideographic signs include, by way of example, traffic signs and the

like.

As used herein in the specification and in the claims section that

follows, the term "translate" refers to any of the following definitions taken from "The American Heritage College Dictionary" (Houghton Mifflin Co..

U.S.A.. Third Edition, 1997):

1. To render in another language;

2a. To put into simpler terms: explain;

2b. To express in different words; paraphrase.

The above-mentioned definitions of the term "translate" refer also to

ideographic signs, such as Japanese kana, and to traffic signs and the like.

The term "translate" also refers to phonetic translation, i.e., a phonetic

representation in the source language or in the target language.

As used herein in the specification and in the claims section that

follows, the term "photographing means" refers to means that are capable of

capturing an image at a distance, and that are characteristically capable of

capturing the entire image in an instantaneous or all-at-once fashion.

Photographing means of the present invention include all kinds of digital

means of capturing an image, including digital cameras (such as digital video

cameras and digital snapshot cameras), and digital binoculars. Specifically

excluded from photographing means are scanners, in which the

image-recording is performed in a gradual fashion, and which require the

object bearing the image to be substantially in contact with the scanning

mechanism.

According to still further features in the described preferred

embodiments, the automatic device of the present invention further comprises an audio device for capturing voice data in the source language, and translation

means for translating the voice data from the source language to the target

language text. Referring to Figure lb, the audio input is conveyed via

microphone 80 to an audio signal digitizing unit 82. The signals are

recognized as words in the recognition unit 84. The words identified in the

recognition unit 84 are subsequently translated into the target language by

translation unit 86. The translated (target language) text is then provided

visually on a display 20. Alternatively, the translated text is passed on to a

speech synthesizer 62 which converts the text into audible speech, which is

then presented to the user by means of a speaker 64.

Although the invention has been described in conjunction with specific

embodiments thereof, it is evident that many alternatives, modifications and

variations will be apparent to those skilled in the art. Accordingly, it is

intended to embrace all such alternatives, modifications and variations that

fall within the spirit and broad scope of the appended claims.

Claims

WHAT IS CLAIMED IS:

1. An automatic device for capturing an image at a distance and

translating text within the image comprising:

(a) photographing means for capturing an image containing a textual

image;

(b) character recognition means for converting said textual image

into corresponding text data written in a source language;

(c) translation means for translating said text data from said source

language to a target language text.

2. The device of claim 1, wherein said target language text is

provided as visual text.

3. The device of claim 2. wherein said visual text is provided on a

visual display.

4. The device of claim 1, wherein said target language text is

provided audially.

5. The device of claim 1. wherein said photographing device is a

digital video camera.

6. The device of claim 1, wherein said photographing device is a digital snapshot camera.

7. The device of claim 1, wherein said translation means for

translating said text data from said source language to a target language text is

provided by accessing the Internet.

8. The device of claim 7, wherein said accessing the Internet is

performed using a Personal Digital Assistant (PDA).

9. The device of claim 7, wherein said accessing the Internet is

performed using a portable computer.

10. The device of claim 7, wherein said accessing the Internet is

performed using a mobile phone.

11. The device of claim 3, wherein said visual display is a visual

display of a mobile phone.

12. The device of claim 1, further comprising:

(d) at least one feature selected from the group consisting of tour

book, business information, language-learning means, map,and travel

directions.

13. The device of claim 1, further comprising:

(d) user-identification means.

14. The device of claim 1. further comprising:

(d) at least one feature selected from the group consisting of

credit card, travel ticket, membership card, car-rental contract, hotel

reservation, and entertainment ticket.

15. The device of claim 1, further comprising:

(d) an audio device for capturing voice data in said source language,

and

(e) translation means for translating said voice data from said source

language to said target language text.

16. The device of claim 15, wherein said target language text is

provided on a visual display.

17. The device of claim 15, wherein said target language text is

provided audially.