CN103928036A - Method and device for generating audio file according to image - Google Patents
Method and device for generating audio file according to image Download PDFInfo
- Publication number
- CN103928036A CN103928036A CN201310013003.4A CN201310013003A CN103928036A CN 103928036 A CN103928036 A CN 103928036A CN 201310013003 A CN201310013003 A CN 201310013003A CN 103928036 A CN103928036 A CN 103928036A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- audio file
- sound
- duration
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Abstract
The invention discloses a method for generating an audio file according to an image, and relates to the technical field of electrons. The image can be represented through the audio file, so that user experience is more diversified. The method includes the steps that a luminance and chrominance image is acquired, wherein the image includes three factor values of each pixel; the tone and audio length corresponding to each pixel are calculated according to any two factor values of the corresponding pixel in the image; the tone and audio length corresponding to each pixel in the image are recorded, so that the audio file is generated. The method and device for generating the audio file according to the image are mainly used in the audio file generating process according to the image.
Description
Technical field
The present invention relates to electronic technology field, relate in particular to a kind of method and device that generates audio file according to image.
Background technology
Electronic multimedia product has brought many different experience to people's live and work, for example, can appreciate photo, Audio and Video by electronic product.
The view data such as photo and video is to represent by the factor values of each pixel, for example, can be red green black (Red Green Black, RGB) image, can be also YC (YUV) image.Taking the image of yuv format as example, for each Y value for pixel, U value and V value representation in image.Wherein, the brightness of Y represent pixel, the colourity of U and V represent pixel.Display device can show the Y value of each pixel, U value and V value by image.
But even image is shown, user also only can appreciate image by vision, the user who brings experiences comparatively single.
Summary of the invention
Embodiments of the invention provide a kind of method and device that generates audio file according to image, can pass through audio presentation image, make user experience more diversification.
For achieving the above object, embodiments of the invention adopt following technical scheme:
An aspect of of the present present invention, provides a kind of method that generates audio file according to image, comprising:
Obtain YC image; Three factor values that wherein said image comprises each pixel;
According to any two factor values of pixel described in described image, calculate the corresponding tone of described pixel and the duration of a sound;
Record the corresponding tone of each described pixel and the duration of a sound in described image, generate audio file.
In conjunction with a first aspect of the present invention, in a kind of possible implementation, described image is red green black RGB image, and three factor values of described image are respectively: red channel R, green channel G and black channel B.
In conjunction with a first aspect of the present invention, in a kind of possible implementation, described image is YC YUV image, and three factor values of described image are respectively: brightness Y and colourity U and V.
In conjunction with a first aspect of the present invention, in a kind of possible implementation, described in obtain image, comprising:
Obtain a picture file as described image;
Or, from video file, obtain a two field picture as described image.
In conjunction with a first aspect of the present invention and above-mentioned possible implementation, in the possible implementation of another kind, describedly calculate the corresponding tone of described pixel and the duration of a sound according to any two factor values of pixel described in described image, comprising:
Determine the corresponding tone of described pixel according to the factor I value of described pixel;
Determine the corresponding duration of a sound of described pixel according to the factor Ⅱ value of described pixel.
In conjunction with a first aspect of the present invention and above-mentioned possible implementation, in the possible implementation of another kind, according to any two factor values of pixel described in described image, after calculating the corresponding tone of described pixel and the duration of a sound, described method also comprises:
Determine the performance speed of described audio file according to the factor III value of the each described pixel in described image.
In conjunction with a first aspect of the present invention and above-mentioned possible implementation, in the possible implementation of another kind, after obtaining image, described method also comprises:
Described pixel in described image is classified according to the interval of three factor values;
Wherein, describedly calculate the corresponding tone of described pixel and the duration of a sound according to any two factor values of pixel described in described image, specifically comprise: respectively to the corresponding tone of each pixel and the duration of a sound in classification described in each classified calculating;
Describedly record the corresponding tone of each described pixel and the duration of a sound in described image, specifically comprise: using each classification as a part, record the corresponding tone of each pixel and the duration of a sound in each classification, generate audio file.
A second aspect of the present invention, provides a kind of device that generates audio file according to image, comprising:
Acquiring unit, for obtaining image; Three factor values that wherein said image comprises each pixel;
Computing unit, for any two factor values of pixel described in the image obtaining according to described acquiring unit, calculates the corresponding tone of described pixel and the duration of a sound;
Generation unit, the described image corresponding tone of each described pixel and the duration of a sound that calculate for recording described computing unit, generate audio file.
In conjunction with a second aspect of the present invention, in a kind of possible implementation, described image is red green black RGB image, and three factor values of described image are respectively: red channel R, green channel G and black channel B.
In conjunction with a second aspect of the present invention, in a kind of possible implementation, described image is YC YUV image, and three factor values of described image are respectively: brightness Y and colourity U and V.
In conjunction with a second aspect of the present invention, in a kind of possible implementation, described acquiring unit, also for:
Obtain a picture file as described image;
Or, from video file, obtain a two field picture as described image.
In conjunction with a second aspect of the present invention and above-mentioned possible implementation, in the possible implementation of another kind, described computing unit, comprising:
Tone subelement, determines the corresponding tone of described pixel for the factor I value of the pixel obtained according to described acquiring unit;
Duration of a sound subelement, determines the corresponding duration of a sound of described pixel for the factor Ⅱ value of the pixel obtained according to described acquiring unit.
In conjunction with a second aspect of the present invention and above-mentioned possible implementation, in the possible implementation of another kind, this device also comprises:
Speed unit, be used at described computing unit according to any two factor values of pixel described in described image, after determining the corresponding tone of described pixel and the duration of a sound, the factor III value of the each described pixel in the image obtaining according to described acquiring unit is determined the performance speed of described audio file.
In conjunction with a second aspect of the present invention and above-mentioned possible implementation, in the possible implementation of another kind, this device also comprises:
Taxon, for classifying the described pixel of described image according to the interval of three factor values;
Wherein, described computing unit specifically for: respectively to described in each classified calculating classification in the corresponding tone of each pixel and the duration of a sound;
Described record cell specifically for: using each classification as a part, record the corresponding tone of each pixel and the duration of a sound in each classification, generate audio file.
What the embodiment of the present invention provided generates method and the device of audio file according to image, obtain image, according to any two factor values of each pixel in described image, calculate the corresponding tone of described pixel and the duration of a sound, thereby generate the audio file that this image is corresponding, can by the content of image by audio presentation out, allow user can pass through auditory perception picture material, make user experience more diversification.
Brief description of the drawings
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is a kind of method flow diagram that generates audio file according to image in the embodiment of the present invention 1;
Fig. 2 is a kind of method flow diagram that generates audio file according to YUV image in the embodiment of the present invention 2;
Fig. 3 is a kind of method flow diagram that generates audio file according to YUV image in the embodiment of the present invention 3;
Fig. 4 is a kind of method flow diagram that generates audio file according to RGB image in the embodiment of the present invention 4;
Fig. 5 is a kind of installation composition schematic diagram that generates audio file according to image in the embodiment of the present invention 5.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiment.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.
Embodiment 1
The embodiment of the present invention provides a kind of method that generates audio file according to image, and as shown in Figure 1, the method can comprise:
101, obtain image; Three factor values that wherein said image comprises each pixel.
Wherein, described image can be red green black RGB image, and three factor values of described image are respectively: red channel R, green channel G and black channel B.Or described image can also be YC YUV image, three factor values of described image are respectively: brightness Y and colourity U and V.The described image that obtains, comprising: obtain a picture file as described image; Or, from video file, obtain a two field picture as described image.Method by the embodiment of the present invention can convert single picture to audio file, also can convert the video being made up of multiple image to audio file.
102, according to any two factor values of pixel described in described image, calculate the corresponding tone of described pixel and the duration of a sound.
Wherein, describedly calculate the corresponding tone of described pixel and the duration of a sound according to any two factor values of each pixel in described image, comprising: determine the corresponding tone of described pixel according to the factor I value of described pixel; Determine the corresponding duration of a sound of described pixel according to the factor Ⅱ value of described pixel.
Further, after calculating the corresponding tone of each pixel and the duration of a sound, can also determine according to the factor III value of the each described pixel in described image the performance speed of described audio file.
103, record the corresponding tone of each described pixel and the duration of a sound in described image, generate audio file.
Further, in order to improve audio frequency effect, can also, before calculating tone and the duration of a sound, first pixel be classified, thus the audio file of generation multi part.Concrete, the each pixel in described image can be classified according to the interval of three factor values; Wherein, described according to any two factor values of each pixel in described image, calculate the corresponding tone of described pixel and the duration of a sound, specifically comprise: according to any two factor values of described pixel, the corresponding tone of each pixel and the duration of a sound that each is classified in this classification respectively; Describedly record the corresponding tone of each described pixel and the duration of a sound in described image, specifically comprise: using each classification as a part, record the corresponding tone of each described pixel and the duration of a sound in each classification, generate audio file.
What the embodiment of the present invention provided generates the method for audio file according to image, obtain image, according to any two factor values of each pixel in described image, calculate the corresponding tone of described pixel and the duration of a sound, thereby generate the audio file that this image is corresponding, can by the content of image by audio presentation out, allow user can pass through auditory perception picture material, make user experience more diversification.
It is pointed out that the mode that uses YUV, sample frequency requires lower, and the efficiency that therefore YUV image is converted to audio file is higher, better user experience.Use the mode of RGB, have relatively high expectations in existing sample frequency, the audio frequency of generation is poor on user's experience property, and therefore, the present invention is not limited to this.
Embodiment 2
The embodiment of the present invention provides a kind of method that generates audio file according to image, and as shown in Figure 2, the method can comprise:
201, obtain YC YUV image.
Wherein, described in obtain YC YUV image, comprising: obtain a picture file as described YUV image; Or, from video file, obtain a two field picture as described YUV image.Method by the embodiment of the present invention can convert single picture to audio file, also can convert the video being made up of multiple image to audio file.Three factor values that described YUV image comprises each pixel, are respectively factor I value, factor Ⅱ value and factor III value.For example, factor I value can be for representing the Y value of brightness, and factor Ⅱ value can be U value, and factor III value can be V value, and wherein U value and V value are two chromatic components.
What deserves to be explained is, obtaining in the process of YUV image, can be in factor values post-sampling U and two factor values of V of determining Y passage, density requirements to sampling is lower, the YUV view data that sampling obtains is less, also less to the calculated amount of the corresponding tone of each pixel and the duration of a sound etc. in YUV image like this, therefore can improve the efficiency that image is converted to audio file.Especially in the time converting the continuous multiple frames image in video file to audio file, can reach higher conversion efficiency, improve the efficiency that image is converted to audio frequency, experience thereby improve user.
202, determine the corresponding tone of described pixel according to the factor I value of described pixel.
Wherein, conventionally tone is divided into treble, middle register and the San Ge range of sound, bass area according to the height of tone, each range of sound respectively includes three octave note spaces, what wherein each note comprised again this note rises semitone, middle pitch and flats, therefore altogether can have: 3 tone=189, note × 3, octave × 7, the range of sound × 3 tone.
In the present embodiment, can adopt dynamic tone mapping mode, the descant that factor I value maximum in all pixels in YUV image and minimum factor I value are corresponded to respectively to 189 tones is in harmonious proportion chest note, be mapped to by also proportional the factor I value of rest of pixels the tone that descant is in harmonious proportion between chest note according to the distribution situation of factor I value in YUV image, thereby obtain the corresponding tone of each pixel.For example, in all pixels of YUV image, the Y value of the highest pixel of brightness is 200, the Y value of the minimum pixel of brightness is 20, so just, can correspond to chest note by 20, corresponding to descant by 200 adjusts, thereby the Y value of all pixels in YUV image is all normalized on 189 tones, obtain the corresponding tone of each pixel in YUV image.
Optionally, also can preset fixing mapping table, preset tone corresponding to all values in factor I value span, thereby obtain tone corresponding to each pixel according to the factor I value query mappings table of each pixel in YUV image.The span of for example Y is 0-255, corresponds to chest note by 0, corresponds to descant and adjusts, thereby the value of Y is normalized on 189 notes by 255, realizes mapping relations.
203, determine the corresponding duration of a sound of described pixel according to the factor Ⅱ value of described pixel.
Wherein, audio file is not only subject to the impact of tone, also has the duration of a sound that important influence factor is exactly each note.In audio frequency playing procedure, being divided into the duration of a sound in 11, for example, can be 2/4 bat and 3/4 bat etc.The duration of a sound difference that each pixel is corresponding, has just embodied the rhythm of audio frequency.Concrete, the factor Ⅱ value of pixel can be normalized in 11 on the duration of a sound.For example, default fixing duration of a sound mapping table, is divided into 11 intervals uniformly by the span of colourity U value, according to U value order from small to large, 11 intervals is grown to long length according to minor respectively and corresponds to 11 kinds of duration of a sound.
204, determine the performance speed of described audio file according to the factor III value of the each described pixel in described YUV image.
Wherein, determined after the tone and the duration of a sound that each pixel is corresponding, the form of expression of audio frequency is also brought different playing effects because performance speed is different.Factor III value can be corresponded in the present embodiment to performance speed.Preferably, for audio frequency is tending towards certain stability to adapt to people's sense of hearing custom, can adopt V value that amplitude of variation is less as factor III value.Because whole audio file can only be determined a performance speed, therefore can go the factor III value of all pixels, average and obtain playing velocity amplitude.For example, the velocity range of performance is set between 15 to 200, can adopt and represent the Y value of brightness or the V value of mark colourity, as the determinative of the speed of performance.Calculate the mean value of the V value of all pixels in YUV image, using this mean value as performance speed.Optionally, difference that also can be between V value maximum in all pixels and minimum V value is as performance speed.
205, record the corresponding tone of each described pixel and the duration of a sound and audio frequency performance speed in described YUV image, generate audio file.
What the embodiment of the present invention provided generates the method for audio file according to image, obtain YUV image, according to any two factor values of each pixel in described YUV image, calculate the corresponding tone of described pixel and the duration of a sound, thereby generate the audio file that this YUV image is corresponding, can by the content of image by audio presentation out, allow user can pass through auditory perception picture material, make user experience more diversification.
And, because the sampling rate of YUV image request is lower, can simplify and carry out the calculated amount that tone and the duration of a sound etc. calculate, thereby improve the efficiency that image is converted to audio file, improve the real-time of conversion, experience thereby further improve user.
Embodiment 3
The embodiment of the present invention provides a kind of method that generates audio file according to image, and as shown in Figure 3, the method can comprise:
301, obtain YC YUV image.
Wherein, described in obtain YC saturation degree YUV image, comprising: obtain a width picture as described YUV image; Or, from video image, obtain a two field picture as described YUV image.Method by the embodiment of the present invention can convert single picture to audio file, also can convert the video being made up of multiple image to audio file.
302, all pixels in described YUV image are classified according to the interval of three factor values.
Wherein, the method of classification can be to be different classification according to the span different demarcation of three factor values, concrete, can be according between V value and the definite chromatic zones of V value, all pixels in YUV image are divided into two kinds of classification of black and white, black classification and white are classified respectively as a part, and for example boy student and schoolgirl, carry out respectively the calculating of tone, the duration of a sound and performance speed to two parts.Finally, two parts are determined respectively to the audio frequency that obtains synthesizes the audio file of and sound effective value.Or, all pixels in YUV image can also be divided into redness, green and blue three color spaces, as three parts.It should be noted that, these are only that several that pixel is classified can also have other mode classifications in practical application for example, the embodiment of the present invention does not limit this.
303, respectively to the corresponding tone of each pixel and the duration of a sound in classification described in each classified calculating.
Wherein, classify as object using each, generate audio frequency corresponding to each classification wherein, described according to any two factor values of each pixel in described YUV image, calculate the corresponding tone of described pixel and the duration of a sound, comprising: determine the corresponding tone of described pixel according to the factor I value of described pixel; Determine the corresponding duration of a sound of described pixel according to the factor Ⅱ value of described pixel.
For example, in the present embodiment, can adopt dynamic tone mapping mode, the descant that factor I value maximum in all pixels in arbitrary classification and minimum factor I value are corresponded to respectively to 189 tones is in harmonious proportion chest note, be mapped to by also proportional the factor I value of rest of pixels the tone that descant is in harmonious proportion between chest note according to the distribution situation of factor I value in this classification, thereby obtain the corresponding tone of each pixel.Concrete become the implementation of audio frequency can be with reference to above-mentioned steps 202-204 to the pixel transitions in each classification respectively, the embodiment of the present invention be no longer described in detail here.
304, using each classification as a part, record the corresponding tone of each described pixel and the duration of a sound in each classification, generate audio file.
Wherein, each part that classification is obtained, carries out respectively similar and audio frequency product process step 202-204, obtains the audio frequency of multiple parts, finally by multiple parts, according to pixel, putting in order in YUV image synthesizes an audio file, obtains the audio file of multi part.
What the embodiment of the present invention provided generates the method for audio file according to image, by obtaining YUV image, according to any two factor values of each pixel in described YUV image, calculate the corresponding tone of described pixel and the duration of a sound, thereby generate the audio file that this YUV image is corresponding, can by the content of image by audio presentation out, allow user can pass through auditory perception picture material, make user experience more diversification.
And, by the whole pixels in image are divided into multiple classification, by a corresponding each classification part, obtain the audio file of multi part, the audio frequency obtaining turning is had and sound effective value, thereby improve user, the sense of hearing of image is experienced.
Embodiment 4
The embodiment of the present invention provides a kind of method that generates audio file according to image, and as shown in Figure 4, the method can comprise:
401, obtain red green black RGB image.
Wherein, described in obtain RGB image, comprising: obtain a picture file as described RGB image; Or, from video file, obtain a two field picture as described RGB image.The described YC saturation degree RGB image that obtains, comprising: obtain a picture file as described RGB image; Or, from video file, obtain a two field picture as described RGB image.Method by the embodiment of the present invention can convert single picture to audio file, also can convert the video being made up of multiple image to audio file.
402, all pixels in described RGB image are classified according to the interval of three factor values.
For example, all pixels in image can be divided into red colour system, green system and black is three major types, thereby in the end generates three parts and audio file sound effective value.Or, can divide according to region, the first half of image is as a part, and the latter half is as part etc., and the embodiment of the present invention does not limit for the division rule of pixel.
403, respectively to the corresponding tone of each pixel and the duration of a sound in classification described in each classified calculating.
404, using each classification as a part, record the corresponding tone of each described pixel and the duration of a sound in each classification, generate audio file.
Wherein, similar with the processing mode of YUV image in the embodiment of Fig. 3, each part that also can obtain classification for RGB image, carry out respectively the audio frequency product process that is similar to step 202-204, obtain the audio frequency of multiple parts, three factor values that different is are here respectively the R factor, G-factor and Factor B.Finally, can by multiple parts, according to pixel, putting in order in RGB image synthesize an audio file, obtain the audio file of multi part.
What the embodiment of the present invention provided generates the method for audio file according to image, by obtaining RGB image, according to any two factor values of each pixel in described RGB image, calculate the corresponding tone of described pixel and the duration of a sound, thereby generate the audio file that this RGB image is corresponding, can by the content of image by audio presentation out, allow user can pass through auditory perception picture material, make user experience more diversification.
And, by the whole pixels in image are divided into multiple classification, by a corresponding each classification part, obtain the audio file of multi part, the audio frequency obtaining turning is had and sound effective value, thereby improve user, the sense of hearing of image is experienced.
Embodiment 5
The embodiment of the present invention provides a kind of device that generates audio file according to image, and as shown in Figure 5, this device can comprise: acquiring unit 51, computing unit 52, generation unit 53.
Acquiring unit 51, for obtaining image; Three factor values that wherein said image comprises each pixel;
Computing unit 52, for any two factor values of pixel described in the image obtaining according to described acquiring unit 51, calculates the corresponding tone of described pixel and the duration of a sound;
Generation unit 53, the described image corresponding tone of each described pixel and the duration of a sound that calculate for recording described computing unit 52, generate audio file.
Further alternative, described image can be red green black RGB image, and three factor values of described image are respectively: red channel R, green channel G and black channel B.Optionally, described image is YC YUV image, and three factor values of described image are respectively: brightness Y and colourity U and V.
Further, described acquiring unit 51, also for: obtain a picture file as described image; Or, from video file, obtain a two field picture as described image.
Further, described computing unit 52, comprising: tone subelement 521, duration of a sound subelement 522.
Tone subelement 521, determines the corresponding tone of described pixel for the factor I value of the pixel obtained according to described acquiring unit 51;
Duration of a sound subelement 522, determines the corresponding duration of a sound of described pixel for the factor Ⅱ value of the pixel obtained according to described acquiring unit 51.
Further, this device also comprises: speed unit 54.
Speed unit 54, be used at described computing unit 52 according to any two factor values of the each pixel of described image, after determining the corresponding tone of described pixel and the duration of a sound, the factor III value of the each described pixel in the image obtaining according to described acquiring unit 51 is determined the performance speed of described audio file.
Further, this device also comprises: taxon 55.
Taxon 55, for classifying all pixels of described image according to the interval of three factor values;
Wherein, described computing unit 52 specifically for: respectively to described in each classified calculating classification in the corresponding tone of each pixel and the duration of a sound;
Described record cell 53 specifically for: using each classification as a part, record the corresponding tone of each pixel and the duration of a sound in each classification, generate audio file.
What the embodiment of the present invention provided generates the device of audio file according to image, by obtaining image, according to any two factor values of each pixel in described image, calculate the corresponding tone of described pixel and the duration of a sound, thereby generate the audio file that this image is corresponding, can by the content of image by audio presentation out, allow user can pass through auditory perception picture material, make user experience more diversification.
And, by the whole pixels in image are divided into multiple classification, by a corresponding each classification part, obtain the audio file of multi part, the audio frequency obtaining turning is had and sound effective value, thereby improve user, the sense of hearing of image is experienced.
Through the above description of the embodiments, those skilled in the art can be well understood to the mode that the present invention can add essential common hardware by software and realize, and can certainly pass through hardware, but in a lot of situation, the former is better embodiment.Based on such understanding, the part that technical scheme of the present invention contributes to prior art in essence in other words can embody with the form of software product, this computer software product is stored in the storage medium can read, as the floppy disk of computing machine, hard disk or CD etc., comprise that some instructions are in order to make a computer equipment (can be personal computer, server, or the network equipment etc.) carry out the method described in each embodiment of the present invention.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited to this, any be familiar with those skilled in the art the present invention disclose technical scope in; can expect easily changing or replacing, within all should being encompassed in protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (14)
1. a method that generates audio file according to image, is characterized in that, comprising:
Obtain image; Three factor values that wherein said image comprises each pixel;
According to any two factor values of pixel described in described image, calculate the corresponding tone of described pixel and the duration of a sound;
Record the corresponding tone of each described pixel and the duration of a sound in described image, generate audio file.
2. the method that generates audio file according to image according to claim 1, is characterized in that,
Described image is red green black RGB image, and three factor values of described image are respectively: red channel R, green channel G and black channel B.
3. the method that generates audio file according to image according to claim 1, is characterized in that,
Described image is YC YUV image, and three factor values of described image are respectively: brightness Y and colourity U and V.
4. according to claim 3ly generate the method for audio file according to image, it is characterized in that, described in obtain image, comprising:
Obtain a picture file as described image;
Or, from video file, obtain a two field picture as described image.
5. according to claim 1ly generate the method for audio file according to image, it is characterized in that, describedly calculate the corresponding tone of described pixel and the duration of a sound according to any two factor values of pixel described in described image, comprising:
Determine the corresponding tone of described pixel according to the factor I value of described pixel;
Determine the corresponding duration of a sound of described pixel according to the factor Ⅱ value of described pixel.
6. according to claim 5ly generate the method for audio file according to image, it is characterized in that, according to any two factor values of pixel described in described image, after calculating the corresponding tone of described pixel and the duration of a sound, described method also comprises:
Determine the performance speed of described audio file according to the factor III value of the each described pixel in described image.
7. according to generating the method for audio file according to image described in any one in claim 1-6, it is characterized in that, after obtaining image, described method also comprises:
All pixels in described image are classified according to the interval of three factor values;
Wherein, describedly calculate the corresponding tone of described pixel and the duration of a sound according to any two factor values of pixel described in described image, specifically comprise: respectively to the corresponding tone of each pixel and the duration of a sound in classification described in each classified calculating;
Describedly record the corresponding tone of each described pixel and the duration of a sound in described image, specifically comprise: using each classification as a part, record the corresponding tone of each pixel and the duration of a sound in each classification, generate audio file.
8. a device that generates audio file according to image, is characterized in that, comprising:
Acquiring unit, for obtaining image; Three factor values that wherein said image comprises each pixel;
Computing unit, for any two factor values of pixel described in the image obtaining according to described acquiring unit, calculates the corresponding tone of described pixel and the duration of a sound;
Generation unit, the described image corresponding tone of each described pixel and the duration of a sound that calculate for recording described computing unit, generate audio file.
9. the device that generates audio file according to image according to claim 8, is characterized in that,
Described image is red green black RGB image, and three factor values of described image are respectively: red channel R, green channel G and black channel B.
10. the device that generates audio file according to image according to claim 8, is characterized in that,
Described image is YC YUV image, and three factor values of described image are respectively: brightness Y and colourity U and V.
11. according to claim 10ly generate the devices of audio file according to image, it is characterized in that, described acquiring unit, also for:
Obtain a picture file as described image;
Or, from video file, obtain a two field picture as described image.
12. devices that generate audio file according to image according to claim 11, is characterized in that, described computing unit, comprising:
Tone subelement, determines the corresponding tone of described pixel for the factor I value of the pixel obtained according to described acquiring unit;
Duration of a sound subelement, determines the corresponding duration of a sound of described pixel for the factor Ⅱ value of the pixel obtained according to described acquiring unit.
13. devices that generate audio file according to image according to claim 12, is characterized in that, also comprise:
Speed unit, determines the performance speed of described audio file for the factor III value of each described pixel of the described image that obtains according to described acquiring unit.
In 14. according to Claim 8-13 described in any one, generate the device of audio file according to image, it is characterized in that, also comprise:
Taxon, for classifying all pixels of described image according to the interval of three factor values;
Wherein, described computing unit specifically for: respectively to described in each classified calculating classification in the corresponding tone of each pixel and the duration of a sound;
Described record cell specifically for: using each classification as a part, record the corresponding tone of each pixel and the duration of a sound in each classification, generate audio file.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310013003.4A CN103928036A (en) | 2013-01-14 | 2013-01-14 | Method and device for generating audio file according to image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310013003.4A CN103928036A (en) | 2013-01-14 | 2013-01-14 | Method and device for generating audio file according to image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103928036A true CN103928036A (en) | 2014-07-16 |
Family
ID=51146233
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310013003.4A Pending CN103928036A (en) | 2013-01-14 | 2013-01-14 | Method and device for generating audio file according to image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103928036A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104918059A (en) * | 2015-05-19 | 2015-09-16 | 京东方科技集团股份有限公司 | Method and device for image transmission and terminal device |
| CN105810209A (en) * | 2016-01-04 | 2016-07-27 | 邱子皓 | Data conversion method based on mapping relation |
| CN107920256A (en) * | 2017-11-30 | 2018-04-17 | 广州酷狗计算机科技有限公司 | Live data playback method, device and storage medium |
| WO2018187890A1 (en) * | 2017-04-09 | 2018-10-18 | 格兰比圣（深圳）科技有限公司 | Method and device for generating music according to image |
| CN108712574A (en) * | 2018-05-31 | 2018-10-26 | 维沃移动通信有限公司 | A kind of method and device playing music based on image |
| CN108805171A (en) * | 2018-05-07 | 2018-11-13 | 广东数相智能科技有限公司 | Image is to the conversion method of music rhythm, device and computer readable storage medium |
| CN108847204A (en) * | 2018-05-07 | 2018-11-20 | 广东数相智能科技有限公司 | The vocal cores production method and music box of music box |
| CN113160781A (en) * | 2021-04-12 | 2021-07-23 | 广州酷狗计算机科技有限公司 | Audio generation method and device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5286908A (en) * | 1991-04-30 | 1994-02-15 | Stanley Jungleib | Multi-media system including bi-directional music-to-graphic display interface |
| CN1287320A (en) * | 1999-09-03 | 2001-03-14 | 北京航空航天大学 | Method of converting image information into music |
| CN1862656A (en) * | 2005-05-13 | 2006-11-15 | 杭州波导软件有限公司 | Method for converting musci score to music output and apparatus thereof |
| CN102289778A (en) * | 2011-05-10 | 2011-12-21 | 南京大学 | Method for converting image into music |
-
2013
- 2013-01-14 CN CN201310013003.4A patent/CN103928036A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5286908A (en) * | 1991-04-30 | 1994-02-15 | Stanley Jungleib | Multi-media system including bi-directional music-to-graphic display interface |
| CN1287320A (en) * | 1999-09-03 | 2001-03-14 | 北京航空航天大学 | Method of converting image information into music |
| CN1862656A (en) * | 2005-05-13 | 2006-11-15 | 杭州波导软件有限公司 | Method for converting musci score to music output and apparatus thereof |
| CN102289778A (en) * | 2011-05-10 | 2011-12-21 | 南京大学 | Method for converting image into music |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104918059A (en) * | 2015-05-19 | 2015-09-16 | 京东方科技集团股份有限公司 | Method and device for image transmission and terminal device |
| CN104918059B (en) * | 2015-05-19 | 2018-07-20 | 京东方科技集团股份有限公司 | Image transfer method and device, terminal device |
| US10547392B2 (en) | 2015-05-19 | 2020-01-28 | Boe Technology Group Co., Ltd. | Terminal device, apparatus and method for transmitting an image |
| CN105810209A (en) * | 2016-01-04 | 2016-07-27 | 邱子皓 | Data conversion method based on mapping relation |
| WO2018187890A1 (en) * | 2017-04-09 | 2018-10-18 | 格兰比圣（深圳）科技有限公司 | Method and device for generating music according to image |
| CN107920256A (en) * | 2017-11-30 | 2018-04-17 | 广州酷狗计算机科技有限公司 | Live data playback method, device and storage medium |
| CN108805171A (en) * | 2018-05-07 | 2018-11-13 | 广东数相智能科技有限公司 | Image is to the conversion method of music rhythm, device and computer readable storage medium |
| CN108847204A (en) * | 2018-05-07 | 2018-11-20 | 广东数相智能科技有限公司 | The vocal cores production method and music box of music box |
| CN108847204B (en) * | 2018-05-07 | 2020-05-22 | 广东数相智能科技有限公司 | Music box and method for manufacturing sound tape of music box |
| CN108805171B (en) * | 2018-05-07 | 2020-11-06 | 广东数相智能科技有限公司 | Method, device and computer readable storage medium for converting image to music melody |
| CN108712574A (en) * | 2018-05-31 | 2018-10-26 | 维沃移动通信有限公司 | A kind of method and device playing music based on image |
| CN113160781A (en) * | 2021-04-12 | 2021-07-23 | 广州酷狗计算机科技有限公司 | Audio generation method and device, computer equipment and storage medium |
| CN113160781B (en) * | 2021-04-12 | 2023-11-17 | 广州酷狗计算机科技有限公司 | Audio generation method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103928036A (en) | Method and device for generating audio file according to image | |
| KR20210015959A (en) | Video signal processing method and apparatus | |
| KR100888473B1 (en) | A method for generating user preference data regarding color characteristic of image | |
| Musburger | Single-camera video production | |
| US20070012165A1 (en) | Method and apparatus for outputting audio data and musical score image | |
| CN106488311B (en) | Sound effect adjusting method and user terminal | |
| CN110444185B (en) | Music generation method and device | |
| CN102123546A (en) | Full-color acousto-optic conversion control method and system | |
| US9076369B2 (en) | Image modulation apparatus, method, and program | |
| US9979766B2 (en) | System and method for reproducing source information | |
| CN110634462B (en) | Sound adjusting system and adjusting method | |
| KR20150112048A (en) | music-generation method based on real-time image | |
| CN101416562A (en) | Combined video and audio based ambient lighting control | |
| CN101727943A (en) | Method and device for dubbing music in image and image display device | |
| US20180352206A1 (en) | Information processing apparatus, information recording medium, information processing method, and program | |
| US10547392B2 (en) | Terminal device, apparatus and method for transmitting an image | |
| KR100893223B1 (en) | Method and apparatus for converting image to sound | |
| US20070269052A1 (en) | Sound enhancement system | |
| CN114003150A (en) | Sound effect display method and terminal equipment | |
| Walton et al. | A subjective comparison of discrete surround sound and soundbar technology by using mixed methods | |
| JP2012060459A (en) | Image processing apparatus, image processing method, program, and recording medium | |
| US10616448B2 (en) | Image processing apparatus performing color conversion process that reflects intention of original color scheme, and control method therefor | |
| JP2012227914A (en) | System and method for natural language assessment of relative color quality | |
| WO2019166030A1 (en) | Smart sound field adaptation system, smart sound field calibration system, and smart speech processing system | |
| JPWO2020066681A1 (en) | Information processing equipment and methods, and programs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140716 |
|
| RJ01 | Rejection of invention patent application after publication |