CN106657817A - Processing method applied to mobile phone platform for automatically making album MV - Google Patents
Processing method applied to mobile phone platform for automatically making album MV Download PDFInfo
- Publication number
- CN106657817A CN106657817A CN201611237751.0A CN201611237751A CN106657817A CN 106657817 A CN106657817 A CN 106657817A CN 201611237751 A CN201611237751 A CN 201611237751A CN 106657817 A CN106657817 A CN 106657817A
- Authority
- CN
- China
- Prior art keywords
- photo
- data
- sift
- processing method
- ssim
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/265—Mixing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/438—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/438—Presentation of query results
- G06F16/4387—Presentation of query results by the use of playlists
- G06F16/4393—Multimedia presentations, e.g. slide shows, multimedia albums
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a processing method applied to a mobile phone platform for automatically making album MV. The method comprises an intelligent picture selection module, an intelligent beautifying effect selection module, a data management module, a rendering module and a video module. by adoption of the method disclosed by the invention, the whole process is automatically processed, a user does not to perform any operation, so that the time cost of the user for making the album MV is zero.
Description
Technical field
The present invention relates to mobile video makes field, in particular, it is related to for a kind of cell phone platform of being applied to
Automatically the processing method of photograph album MV is made.
Background technology
In recent years smart mobile phone becomes increasingly popular, and its function is also stronger and stronger, and in daily life it instead of substantially
Camera function.Meanwhile, people are fabricated to photograph album MV and are shared with that relatives and friends are also little by little popular to rise the photo that mobile phone shoots
Come.The making of traditional photograph album MV, needs user that the picture for making photograph album MV is selected from the photograph album of mobile phone, then from very
Certain landscaping effect of matching photo scene is selected in many landscaping effects by repeatedly trial, subsequently from many music
In pick out matching photo scene music as MV background sound.
When making photograph album MV automatically in actual life, user has clapped a photo and can first have a look effect, if effect
It is bad to attempt clapping one again, until photographing oneself satisfaction till, this also can cause to exist in mobile phone photo album a lot
Similar photo.Therefore the shortcoming of this scheme is that user needs longer time to make MV into original, and secondly user selects manually
The landscaping effect selected and music not necessarily match the scene of photo.So two problems in the urgent need to address:How first point be
Similar photo is removed, how second point selects the landscaping effect and background sound for matching photo scene.
The content of the invention
It is an object of the invention to provide a kind of processing method of the automatic making photograph album MV for being applied to cell phone platform so that
The fully automated process of whole process, it is not necessary to any operation of user, makes the time cost that user makes photograph album MV to be 0.
In order to solve above-mentioned technical problem, technical scheme is as follows:
A kind of processing method of the automatic making photograph album MV for being applied to cell phone platform, specifically includes following steps:
101) Intelligent Selection figure:The Intelligent Selection figure, by the photo in a period of time unduplicated photo is selected, and automatically
The photo list that generation is chosen, and photo table data is passed to data management module;
102) intelligence beautification:By step 101) select photo by artificial intelligence deep learning method process, then oneself
It is dynamic to select landscaping effect and background music, and corresponding data are transferred to into data management module;
103) data management:By step 101) and 102) data that generate carry out storage and call management;
104) render:By step 103) data message of needs is obtained in data, and they are rendered to one by one
Vedio data;
105) video being generated, by step 104) data compression that generates, into corresponding video data encoder, and writes video
File, generates MV.
Further, the step 101) in Intelligent Selection figure the step of it is as follows:
201) access time section:The all photos shot in a period of time are selected from user mobile phone photograph album;
202) photo sequence:Step 201) generate photo be temporally from morning to night ranked up;
203) photo is screened:Step 202) the photo application photo similarity processing method that sorted shines to judge to choose
Piece, the similarity processing method includes SSIM and SIFT, and comprehensive both are screened, and thus obtain removing after similar photo
Target picture;The SSIM full name are structural similarity index structural similarities, are a kind of two width figures of measurement
As the index of similarity;It is Scale-invariant feature that the SIFT is Scale invariant features transform full name
Transform, for one kind description of image processing field.
Further, the method that both described synthesis are screened is as follows:
The numerical value that SSIM (x, y) and SIFT (x, y) are obtained is transformed into into 0 to 100 number;
If SIFT (x, y)>50, return SIFT (x, y);
If SIFT (x, y)>40, return SIFT (x, y) * 0.5+SSIM (x, y) * 0.5;
If SIFT (x, y)>30, return SIFT (x, y) * 0.25+SSIM (x, y) * 0.75;
If SIFT (x, y)>20, return SIFT (x, y) * 0.125+SSIM (x, y) * 0.875;
Otherwise, SSIM (x, y) is returned;
The data value for finally returning that is not less than 50, represent two figures be it is similar, it is otherwise, dissimilar.
Further, the SSIM is a kind of index of two width image similarities of measurement, and the concrete grammar that SSIM compares is
Equation below (1):
Wherein x, y are two images for comparing, μxIt is the mean value of x, μyIt is the mean value of y, δx 2It is the variance of x,
δy 2It is the variance of y, δxyIt is the standard deviation of x and y.c1=(k1L)2,c2=(k2L)2It is for maintaining stable constant, k1、k2It is
Constant, L is the scope of pixel value, depending on the size of real image pixel.
Further, the SIFT is Scale invariant features transform, for one kind description of image processing field;SIFT is special
Levy the concrete grammar equation below (2) for comparing:
Wherein x, y are two images for comparing, niIt is characterized a number, nfIt is image x two picture registration parts
The number of interior all characteristic points, α, β are constant;The niAccording to RANSAC methods obtain two images transformation matrix H and
Feature point number n of matchingi, the RANSAC methods are the sample data set comprising abnormal data according to one group, calculate number
According to mathematical model parameter, the method for obtaining effective sample data, the nfObtained according to transformation matrix H.
Further, the step 102) intelligence beautification method it is as follows:
501) photo is read:From step 101) generate photo list in read a photo;
502) object is recognized:Step 501) photo that obtains identifies main thing by artificial intelligence deep learning method
Body, and set up object list data;
503) weighting is sorted out:According to step 502) set up table data, successively according to listed object according to respective rule
Scene classification is carried out, and weighting carries out statistical computation;
504) scene is selected:According to step 503) result of statistical computation is carried out into scene selection, beautification effect is chosen automatically
Fruit and background sound.
Further, the step 502) in artificial intelligence deep learning method adopt Deep Learning intelligence sides
Method or deep neural network.
Further, the step 504) in landscaping effect and background sound matching will be stamped to it in database
Their scene tag.
Further, the step 103) in data management include photo files, background sound file, landscaping effect
The storage of configuration file, and for step 104) render the data that input is provided.
Compared to existing technology advantage is the present invention:
1, the fully automated process of whole process, it is not necessary to any operation of user makes user make the time cost of photograph album MV
To be 0.
2. Intelligent Selection module is applied, and it is that user is satisfied generally to select the photo for coming.
3. the intelligent landscaping effect selecting module of application, with the landscaping effect and background sound of matching photo, produces fineness
Photograph album MV.
4. intelligent processing method is adopted, the photograph album MV for producing can consider more factors, making typically manual than user
It is more preferable.
Description of the drawings
Fig. 1 is a kind of process chart of the processing method of the automatic making photograph album MV for being applied to cell phone platform of the present invention;
Fig. 2 is a kind of stream of the Intelligent Selection figure of the processing method of the automatic making photograph album MV for being applied to cell phone platform of the present invention
Cheng Tu;
Fig. 3 is a kind of stream of the intelligence beautification of processing method of the automatic making photograph album MV for being applied to cell phone platform of the present invention
Cheng Tu.
Specific embodiment
With reference to the accompanying drawings and detailed description the present invention is further described.
As shown in figure 1, a kind of processing method of the automatic making photograph album MV for being applied to cell phone platform, specifically includes following step
Suddenly:
101) Intelligent Selection figure:The Intelligent Selection figure, by the photo in a period of time unduplicated photo is selected, and automatically
The photo list that generation is chosen, and photo table data is passed to data management module.As shown in Fig. 2 the tool of Intelligent Selection figure
Body step is as follows:
201) access time section:The all photos shot in a period of time are selected from user mobile phone photograph album.
202) photo sequence:Step 201) generate photo be temporally from morning to night ranked up, this is sequentially exactly
The precedence of user's actual photographed these photos.
203) photo is screened:Step 202) the photo application photo similarity processing method that sorted shines to judge to choose
Piece, the similarity processing method includes SSIM and SIFT, and comprehensive both are screened, i.e., previous similar with next Zhang Jinhang
Degree judges and screens, if both are dissimilar, then previous is selected into, otherwise previous discarding, then latter and it after
One carry out similarity judgement and screening again, by that analogy.Thus finally give and remove the target picture after similar photo.
SSIM (the structural similarity index) structural similarity, is a kind of two width image phases of measurement
Like the index of degree, the concrete grammar that SSIM compares is equation below (1):
Wherein x, y are two images for comparing, μxIt is the mean value of x, μyIt is the mean value of y, δx 2It is the variance of x,
δy 2It is the variance of y, δxyIt is the standard deviation of x and y.c1=(k1L)2,c2=(k2L)2It is for maintaining stable constant, k1、k2It is
Constant, L is the scope of pixel value, depending on the size of real image pixel.
The SIFT is Scale invariant features transform (Scale-invariant feature transform, SIFT), is used
In one kind description of image processing field;The concrete grammar equation below (2) that SIFT feature compares:
Wherein x, y are two images for comparing, niIt is characterized a number, nfIt is image x two picture registration parts
The number of interior all characteristic points, α, β are constant;The niAccording to RANSAC methods obtain two images transformation matrix H and
Feature point number n of matchingi, the RANSAC methods are the sample data set comprising abnormal data according to one group, calculate number
According to mathematical model parameter, the method for obtaining effective sample data, the nfObtained according to transformation matrix H.
Comprehensive SSIM and SIFT will the expression of SSIM and SIFT be respectively SSIM (x, y) and SIFT (x, y), and
The numerical value that SSIM (x, y) and SIFT (x, y) are obtained is transformed into 0 to 100 number, i.e. SSIM (x, y) and obtains 0 to 100 number, SIFT
(x, y) obtains 0 to 100 number.
If SIFT (x, y)>50, return SIFT (x, y);
If SIFT (x, y)>40, return SIFT (x, y) * 0.5+SSIM (x, y) * 0.5;
If SIFT (x, y)>30, return SIFT (x, y) * 0.25+SSIM (x, y) * 0.75;
If SIFT (x, y)>20, return SIFT (x, y) * 0.125+SSIM (x, y) * 0.875;
Otherwise, SSIM (x, y) is returned.
As long as the data value for finally returning that is not less than 50, represent two figures be it is similar, it is otherwise, dissimilar.
102) intelligence beautification, by step 101) select photo by artificial intelligence deep learning method process, this will knowledge
The primary objects list not gone out in single photo, according to the object list for identifying, identifies that the photo likelihood ratio is higher
Scene.For example, if the tree etc. that has mountain and water in object list may be considered tourism scene, if there is child in object list
May be considered mother and baby's scene.Then the scene for going out to all photo arrays again, by scene type weighted statistical, weights highest
Scene is exactly the scene for screening photo.Then landscaping effect and background music are automatically selected, and by corresponding data transfer
To data management module.As shown in figure 3, the concrete grammar step of intelligence beautification is as follows:
501) photo is read:From step 101) generate photo list in read a photo;
502) object is recognized:Step 501) photo that obtains identifies main thing by artificial intelligence deep learning method
Body, and set up object list data.The artificial intelligence deep learning method is using Deep Learning intelligent methods or depth
Neutral net.
503) weighting is sorted out:According to step 502) set up table data, successively according to listed object according to respective rule
Scene classification is carried out, and weighting carries out statistical computation.
504) scene is selected:According to step 503) result of statistical computation is carried out into scene selection, beautification effect is chosen automatically
Fruit and background sound.Landscaping effect therein and background sound will be stamped to it in database and match their scene mark
Sign, when the result of statistical computation carries out obtaining consistent with the label of scene after scene selection, arbitrarily select a landscaping effect and
Background sound gives photograph album MV.
103) data management:By step 101) and 102) data that generate carry out storage and call management.Data include photo
File, background sound file, the storage of the configuration file of landscaping effect, and the data that input is provided are rendered for step 104.
104) render:By step 103) data message of needs is obtained in data, and they are rendered to one by one
Vedio data.
105) video is generated:By step 104) generate vedio data Video coding number is compressed into by encryption algorithm
According to, and these data are write in last video file, generate MV.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
Member, without departing from the inventive concept of the premise, can also make some improvements and modifications, and these improvements and modifications also should be regarded as
In the scope of the present invention.
Claims (9)
1. a kind of processing method of the automatic making photograph album MV for being applied to cell phone platform, it is characterised in that specifically include following step
Suddenly:
101) Intelligent Selection figure:The Intelligent Selection figure, by the photo in a period of time unduplicated photo is selected, and is automatically generated
The photo list chosen, and photo table data is passed to data management module;
102) intelligence beautification:By step 101) select photo by artificial intelligence deep learning method process, then select automatically
Landscaping effect and background music are selected, and corresponding data are transferred to into data management module;
103) data management:By step 101) and 102) data that generate carry out storage and call management;
104) render:By step 103) obtain the data message of needs in data, and they are rendered to video one by one
View data;
105) video is generated:By step 104) data compression that generates, into corresponding video data encoder, and writes video file,
Generate MV.
2. the processing method of a kind of automatic making photograph album MV for being applied to cell phone platform according to claim 1, its feature
Be, the step 101) in Intelligent Selection figure the step of it is as follows:
201) access time section:The all photos shot in a period of time are selected from user mobile phone photograph album;
202) photo sequence:Step 201) generate photo be temporally from morning to night ranked up;
203) photo is screened:Step 202) the photo application photo similarity processing method that sorted judging to choose photo,
The similarity processing method includes SSIM and SIFT, and comprehensive both are screened, and thus obtain removing the mesh after similar photo
Mark photo;The SSIM full name are structural similarity index structural similarities, are a kind of two width images of measurement
The index of similarity;It is Scale-invariant feature that the SIFT is Scale invariant features transform full name
Transform, for one kind description of image processing field.
3. the processing method of a kind of automatic making photograph album MV for being applied to cell phone platform according to claim 2, its feature
It is that the method that both described synthesis are screened is as follows:
The numerical value that SSIM (x, y) and SIFT (x, y) are obtained is transformed into into 0 to 100 number;
If SIFT (x, y)>50, return SIFT (x, y);
If SIFT (x, y)>40, return SIFT (x, y) * 0.5+SSIM (x, y) * 0.5;
If SIFT (x, y)>30, return SIFT (x, y) * 0.25+SSIM (x, y) * 0.75;
If SIFT (x, y)>20, return SIFT (x, y) * 0.125+SSIM (x, y) * 0.875;
Otherwise, SSIM (x, y) is returned;
The data value for finally returning that is not less than 50, represent two figures be it is similar, it is otherwise, dissimilar.
4. the processing method of a kind of automatic making photograph album MV for being applied to cell phone platform according to claim 2, its feature
It is that the SSIM is a kind of index of two width image similarities of measurement, the concrete grammar that SSIM compares is equation below (1):
Wherein x, y are two images for comparing, μxIt is the mean value of x, μyIt is the mean value of y, δx 2It is the variance of x, δy 2It is y
Variance, δxyIt is the standard deviation of x and y.c1=(k1L)2,c2=(k2L)2It is for maintaining stable constant, k1、k2It is constant, L
It is the scope of pixel value, depending on the size of real image pixel.
5. the processing method of a kind of automatic making photograph album MV for being applied to cell phone platform according to claim 2, its feature
It is that the SIFT is Scale invariant features transform, for one kind description of image processing field;It is concrete that SIFT feature compares
Method equation below (2):
Wherein x, y are two images for comparing, niIt is characterized a number, nfIt is image x in two picture registration parts
The number of all characteristic points, α, β are constant;The niTransformation matrix H and the matching of two images are obtained according to RANSAC methods
Feature point number ni, the RANSAC methods are the sample data set comprising abnormal data according to one group, calculate data
Mathematical model parameter, the method for obtaining effective sample data, the nfObtained according to transformation matrix H.
6. the processing method of a kind of automatic making photograph album MV for being applied to cell phone platform according to claim 1, its feature
Be, the step 102) intelligence beautification method it is as follows:
501) photo is read:From step 101) generate photo list in read a photo;
502) object is recognized:Step 501) photo that obtains identifies primary objects by artificial intelligence deep learning method, and
Set up object list data;
503) weighting is sorted out:According to step 502) set up table data, carried out according to respective rule according to listed object successively
Scene is sorted out, and weighting carries out statistical computation;
504) scene is selected:According to step 503) result of statistical computation is carried out into scene selection, choose automatically landscaping effect and
Background sound.
7. the processing method of a kind of automatic making photograph album MV for being applied to cell phone platform according to claim 6, its feature
Be, the step 502) in artificial intelligence deep learning method using Deep Learning intelligent methods or depth nerve
Network.
8. the processing method of a kind of automatic making photograph album MV for being applied to cell phone platform according to claim 6, its feature
Be, the step 504) in landscaping effect and background sound it will be stamped in database matching their scene mark
Sign.
9. the processing method of a kind of automatic making photograph album MV for being applied to cell phone platform according to claim 1, its feature
Be, the step 103) in data management include that photo files, background sound file, the configuration file of landscaping effect are deposited
Storage, and for step 104) render the data that input is provided.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611237751.0A CN106657817A (en) | 2016-12-28 | 2016-12-28 | Processing method applied to mobile phone platform for automatically making album MV |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611237751.0A CN106657817A (en) | 2016-12-28 | 2016-12-28 | Processing method applied to mobile phone platform for automatically making album MV |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106657817A true CN106657817A (en) | 2017-05-10 |
Family
ID=58832065
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611237751.0A Pending CN106657817A (en) | 2016-12-28 | 2016-12-28 | Processing method applied to mobile phone platform for automatically making album MV |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106657817A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109167937A (en) * | 2018-11-05 | 2019-01-08 | 北京达佳互联信息技术有限公司 | Video distribution method, apparatus, terminal and storage medium |
WO2019062716A1 (en) * | 2017-09-30 | 2019-04-04 | 腾讯科技(深圳)有限公司 | Method and apparatus for generating music |
CN110246523A (en) * | 2019-04-26 | 2019-09-17 | 广东虎彩影像有限公司 | A kind of video generating system and its method |
CN111309957A (en) * | 2020-03-17 | 2020-06-19 | 杭州趣维科技有限公司 | Method for automatically generating travel photo album MV |
CN112463998A (en) * | 2020-11-25 | 2021-03-09 | 京东方科技集团股份有限公司 | Album resource processing method, apparatus, electronic device and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102073985A (en) * | 2010-12-23 | 2011-05-25 | 清华大学 | Method and device for objectively evaluating scaled image quality by matching pixel points |
CN104202661A (en) * | 2014-09-15 | 2014-12-10 | 厦门美图之家科技有限公司 | Automatic picture-to-video conversion method |
CN104268547A (en) * | 2014-08-28 | 2015-01-07 | 小米科技有限责任公司 | Method and device for playing music based on picture content |
CN105224409A (en) * | 2015-09-30 | 2016-01-06 | 努比亚技术有限公司 | A kind of management method of internal memory and device |
CN105989599A (en) * | 2015-02-15 | 2016-10-05 | 西安酷派软件科技有限公司 | Image processing method and apparatus, and terminal |
-
2016
- 2016-12-28 CN CN201611237751.0A patent/CN106657817A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102073985A (en) * | 2010-12-23 | 2011-05-25 | 清华大学 | Method and device for objectively evaluating scaled image quality by matching pixel points |
CN104268547A (en) * | 2014-08-28 | 2015-01-07 | 小米科技有限责任公司 | Method and device for playing music based on picture content |
CN104202661A (en) * | 2014-09-15 | 2014-12-10 | 厦门美图之家科技有限公司 | Automatic picture-to-video conversion method |
CN105989599A (en) * | 2015-02-15 | 2016-10-05 | 西安酷派软件科技有限公司 | Image processing method and apparatus, and terminal |
CN105224409A (en) * | 2015-09-30 | 2016-01-06 | 努比亚技术有限公司 | A kind of management method of internal memory and device |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019062716A1 (en) * | 2017-09-30 | 2019-04-04 | 腾讯科技(深圳)有限公司 | Method and apparatus for generating music |
US11301641B2 (en) | 2017-09-30 | 2022-04-12 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for generating music |
CN109167937A (en) * | 2018-11-05 | 2019-01-08 | 北京达佳互联信息技术有限公司 | Video distribution method, apparatus, terminal and storage medium |
CN109167937B (en) * | 2018-11-05 | 2022-10-14 | 北京达佳互联信息技术有限公司 | Video distribution method, device, terminal and storage medium |
CN110246523A (en) * | 2019-04-26 | 2019-09-17 | 广东虎彩影像有限公司 | A kind of video generating system and its method |
CN111309957A (en) * | 2020-03-17 | 2020-06-19 | 杭州趣维科技有限公司 | Method for automatically generating travel photo album MV |
CN112463998A (en) * | 2020-11-25 | 2021-03-09 | 京东方科技集团股份有限公司 | Album resource processing method, apparatus, electronic device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111539370B (en) | Image pedestrian re-identification method and system based on multi-attention joint learning | |
CN106919920B (en) | Scene recognition method based on convolution characteristics and space vision bag-of-words model | |
CN106776662B (en) | Photo sorting method and device | |
JP5170961B2 (en) | Image processing system, image processing apparatus and method, program, and recording medium | |
Bianco et al. | Improving color constancy using indoor–outdoor image classification | |
US8712157B2 (en) | Image quality assessment | |
CN100517328C (en) | Display control device and method | |
US20080285860A1 (en) | Studying aesthetics in photographic images using a computational approach | |
CN109816009A (en) | Multi-tag image classification method, device and equipment based on picture scroll product | |
CN106657817A (en) | Processing method applied to mobile phone platform for automatically making album MV | |
CN110415184B (en) | Multi-modal image enhancement method based on orthogonal element space | |
CN110555527A (en) | Method and equipment for generating delayed shooting video | |
JP2019016114A (en) | Image processing device, learning device, focus controlling device, exposure controlling device, image processing method, learning method and program | |
CN111833360B (en) | Image processing method, device, equipment and computer readable storage medium | |
CN110351597A (en) | A kind of method, apparatus and electronic equipment of video clipping | |
Liu et al. | Overview of image inpainting and forensic technology | |
CN115713546A (en) | Lightweight target tracking algorithm for mobile terminal equipment | |
CN105095468A (en) | Novel image retrieval method and system | |
CN112035685B (en) | Album video generating method, electronic device and storage medium | |
JP6109118B2 (en) | Image processing apparatus and method, information processing apparatus and method, and program | |
Raihan et al. | CNN modeling for recognizing local fish | |
Zenoozi et al. | Argan: fast converging gan for animation style transfer | |
CN114707055A (en) | Photographing posture recommendation method integrating image content and feature extraction | |
CN115115979A (en) | Identification and replacement method of component elements in video and video recommendation method | |
CN114445916A (en) | Living body detection method, terminal device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |
|
RJ01 | Rejection of invention patent application after publication |