CN107153838A - A kind of photo automatic grading method and device - Google Patents
A kind of photo automatic grading method and device Download PDFInfo
- Publication number
- CN107153838A CN107153838A CN201710257193.2A CN201710257193A CN107153838A CN 107153838 A CN107153838 A CN 107153838A CN 201710257193 A CN201710257193 A CN 201710257193A CN 107153838 A CN107153838 A CN 107153838A
- Authority
- CN
- China
- Prior art keywords
- photograph image
- image
- photograph
- photo
- scoring
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
- G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of photo automatic grading method and device.This method includes:Smart machine photograph image is obtained, aesthstic scoring is carried out to the photograph image, grade and the display of the photograph image are obtained according to the aesthetics scoring.The present invention can realize the classification of photograph album by carrying out aesthetics scoring to photo so that photograph album more easily retrieves gratifying high-quality photos;The automatic aesthetics scoring of the local photograph album photo of smart machine and camera live view image can be applied to;The aesthetics classification of photograph album is more accurate, more comprehensive, and easy to operate, efficiency high, effectively overcomes various shortcoming of the prior art and has high industrial utilization.
Description
Technical field
Technical field of image processing of the present invention, more particularly to a kind of photo automatic grading method and device.
Background technology
The photo that user stores in personal device now is more and more, and fast searching goes out shooting effect from magnanimity photo
Relatively satisfactory photo takes time and effort, it is therefore desirable to it is a kind of can be from the method for aesthstic angle automatic classification photo.Have at present
The application that photograph album can be automatically managed and patent of invention.Apple Inc. iOS10 systems can be according to identifying
Photo content is classified automatically.Application No. CN201510827259.8 invention carries out image knowledge to the photograph in photograph album
Not, photograph is classified as portrait classification or landscape classification;The photographing information of photograph in photograph album is obtained, will according to the photographing information
The photograph of portrait classification is classified as auto heterodyne portrait classification again or he claps portrait classification, and the photograph of landscape classification is classified as into a day scape again
Classification or night scene classification.The invention recognizes to carry out the classification of photographic content by the real-time intelligent to photograph so that photograph album is more
Plus it is clean and tidy, but in face of the uneven photo of magnanimity quality, it is impossible to realize the classification that photographic quality is carried out from aesthstic angle.Shen
Please number for CN201210359524.0 invention first using based on power spectral tilt method extract sample photo motif area,
Then the feature of sample photo is extracted, the final training that photo aesthetic quality is carried out using support vector machine grader is divided
INTERFACE MODEL;Automatic assorting process is identified using boundary surface model.The invention considers the thinking classified from aesthstic angle,
But it is not comprehensive by the feature manually extracted, with certain subjectivity and one-sidedness, and general identification tactic is taken
Without being handled differently for photo scene, because the aesthetic evaluation standard of different photo scenes should be differentiated, therefore
Classification performance is limited.
The content of the invention
In view of the above problems, the invention provides a kind of photo automatic grading method and device.
A kind of photo automatic grading method that the present invention is provided, including:
Obtain smart machine photograph image;
Aesthstic scoring is carried out to the photograph image, is scored according to the aesthetics, obtains the grade of the photograph image simultaneously
Display.
Present invention also offers a kind of photo self-grading device, including photograph image acquisition module, grade classification module:
The photograph image acquisition module, for obtaining smart machine photograph image;
The grade classification module, for carrying out aesthstic scoring to the photograph image, scores according to the aesthetics, obtains
The grade of the photograph image and display.
The present invention has the beneficial effect that:
The embodiment of the present invention solves not realizing in the prior art from U.S. by carrying out photograph image aesthstic scoring, effectively
Learn angle and carry out the classification of photographic quality or although it is contemplated that the thinking classified from aesthstic angle, but it is by manually carrying
The feature taken is not comprehensive, the problem of with certain subjectivity and one-sidedness, has industrial utilization.
Brief description of the drawings
Fig. 1 is the flow chart of the photo automatic grading method of the inventive method embodiment;
Fig. 2 is the flow chart that photograph image is identified and analyzed in the inventive method embodiment;
Fig. 3 is the structural representation of the photo self-grading device of apparatus of the present invention embodiment.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
In order to solve can not to realize in the prior art from aesthstic angle carry out photographic quality classification or although it is contemplated that
The thinking classified from aesthstic angle, but it is not comprehensive by the feature manually extracted, with certain subjectivity and unilateral
The problem of property, the invention provides a kind of photo automatic grading method and device, below in conjunction with accompanying drawing and embodiment, to this hair
It is bright to be further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, do not limit
The fixed present invention.
The method according to the invention embodiment is there is provided a kind of photo automatic grading method, and Fig. 1 is that the inventive method is implemented
The flow chart of the photo automatic grading method of example, as shown in figure 1, according to the photo automatic grading method of the inventive method embodiment
Including following processing:
Step 101, smart machine photograph image is obtained.
Specifically, smart machine include PC, smart mobile phone, tablet personal computer, intelligent glasses, and other have take the photograph
As the equipment of head and data processing function.
Specifically, the photograph image is the photograph image or smart machine live view photo that have preserved in smart machine
Image.
Step 102, aesthstic scoring is carried out to the photograph image, is scored according to the aesthetics, obtains the photograph image
Grade and display.
Specifically, the photo figure grade is graphical cues and/or text prompt and/or voice message.
When the photograph image is live view photograph image, the grade of the photograph image is shown, so that user selects
Select and whether take pictures.
Comprise the following steps specifically, carrying out aesthetics scoring to the photograph image:
The photograph image is input in default aesthetic evaluation model, the aesthetics scoring of the photograph image is obtained.
As another embodiment of the inventive method embodiment, before aesthstic scoring is carried out to the photograph image, go back
Comprise the following steps:
Using default image scene classification algorithm, the photograph image is identified and analyzed, the photo is obtained
The classification results of the affiliated scene of image;
Further, aesthetics scoring is carried out to the photograph image to comprise the following steps:
The photograph image and the classification results of the affiliated scene of the photograph image (such as scene tag) are input to pre-
If aesthetic evaluation model in, obtain the photograph image aesthetics scoring.
The default aesthetic evaluation model is obtained by training, and the machine learning method used includes convolutional Neural net
Network, limited Boltzmann machine, depth confidence network etc..
Further, the training method of the aesthetic evaluation model comprises the following steps:
Obtain several images of known aesthetics scoring;
Default aesthetic evaluation model is trained using several images of known aesthetics scoring, or utilizes known U.S.
The scene tag belonging to several images and image of scoring is learned to be trained default aesthetic evaluation model.
As shown in Fig. 2 specifically, using default image scene classification algorithm, the photograph image is identified and
Analysis, the classification results for obtaining the affiliated scene of the photograph image comprise the following steps:
S201:Several objects in the photograph image are identified by default object recognition algorithm;
S202:Association between several objects according to being analyzed default context semantic model;
S203:According to the result of analysis, the classification results of the affiliated scene of photograph image are obtained.
It is further comprising the steps of as another embodiment of the inventive method embodiment:When the photograph image is intelligence
During the photograph image preserved in equipment, scored according to the aesthetics of several photograph images preserved in smart machine, to institute
Several photograph images are stated to be classified (i.e. the classification of photograph album).
The embodiment of the present invention can realize the classification of photograph album by carrying out aesthetics scoring to photograph image so that photograph album is more
It is easy to retrieve gratifying high-quality photos;The local photograph album photo of smart machine and camera live view can be applied to
The automatic aesthetics scoring of image;The aesthetics classification of photograph album is more accurate, more comprehensive, and easy to operate, efficiency high, effectively overcomes
Various shortcoming of the prior art and have high industrial utilization.
Apparatus according to the invention embodiment is there is provided a kind of photo self-grading device, and Fig. 3 is that apparatus of the present invention are implemented
The structural representation of the photo self-grading device of example, as shown in figure 3, according to the photo automatic classification of apparatus of the present invention embodiment
Device includes:The modules of the embodiment of the present invention are carried out in detail by photograph image acquisition module 30, grade classification mould 32 below
Explanation.
Specifically, the photograph image acquisition module 30, for obtaining smart machine photograph image.
The grade classification module 32, for carrying out aesthstic scoring to the photograph image, scores according to the aesthetics, obtains
Grade and display to the photograph image.
Specifically, the photograph image grade is graphical cues and/or text prompt and/or voice message.
The grade classification module 32 specifically for:
The photograph image is input in default aesthetic evaluation model, the aesthetics scoring of the photograph image is obtained.
It is used as another embodiment of apparatus of the present invention embodiment, in addition to image scene classification module:
Described image scene classification module, for using default image scene classification algorithm, enters to the photograph image
Row identification and analysis, obtain the classification results of the affiliated scene of the photograph image;
The grade classification module 32 is additionally operable to:
The photograph image and the classification results of the affiliated scene of the photograph image (such as scene tag) are input to pre-
If aesthetic evaluation model in, obtain the photograph image aesthetics scoring.
Specifically, described image scene classification module is used for:
Several objects in the photograph image are identified by default object recognition algorithm;
Association between several objects according to being analyzed default context semantic model;
According to the result of analysis, the classification results of the affiliated scene of photograph image are obtained.
Specifically, the default aesthetic evaluation model includes convolutional neural networks model, limited Boltzmann machine, depth
Confidence network.
The default aesthetic evaluation model is obtained by training, and the machine learning method used includes convolutional Neural net
Network, limited Boltzmann machine, depth confidence network etc..
It is used as another embodiment of apparatus of the present invention embodiment, in addition to model training module:
The model training module is used for:
Obtain several images of known aesthetics scoring;
Default aesthetic evaluation model is trained using several images of known aesthetics scoring, or utilizes known U.S.
The scene tag belonging to several images and image of scoring is learned to be trained default aesthetic evaluation model.
It is used as another embodiment of apparatus of the present invention embodiment, in addition to sort module, the sort module, for working as
During the photograph image for stating photograph image to have preserved in smart machine, according to several photograph images preserved in smart machine
Aesthetics scoring, several described photograph images are classified.
The smart machine photograph album photo automatic grading method and system of the present invention, has the advantages that:
1st, adaptively aesthetic evaluation, and avoid taking general aesthetics is carried out to different scenes using scene classification algorithm
The classification performance limitation of identification tactic, improves the accuracy of final photograph album photo classification.
2nd, aesthetic evaluation model is obtained by training, it is to avoid the subjectivity and one-sidedness of artificial rule model.
For the more detailed explanation embodiment of the present invention, example 1 is provided, example 1 comprises the following steps:
Step S1:Photograph image is obtained from smart machine photograph album.
Step S2:Using image scene classification algorithm, image recognition is carried out to the photograph in photograph album, will according to recognition result
Photo is divided into landscape, portrait, night scene, building, animal, plant, dynamic, static state, nine classifications of backlight.
Step S3:According to the result of scene classification and original image as input, convolutional neural networks aesthetic evaluation is used
Model carries out further aesthetic evaluation, obtains the aesthetics scoring of photo.
Step S4:Score value height correspondence aesthetic values height, can be quantified as some grades according to scoring score value, facilitate user
Retrieval.
In step sl, photograph image is obtained in smart machine photograph album, can also obtains smart machine camera live view
Image is used as image sources.
In step s 2, the result gone out according to scene classification Algorithm Analysis can be by graphic collection landscape, portrait, night scene,
Building, animal, plant, dynamic, static state, nine classifications of backlight, that is, obtain the affiliated scene classification result of photo.
It should be noted that having there is the scene classification of many maturations in the prior art, therefore it will not be repeated here.
In the step S3, it will be inputted as image scene classification result, and use convolutional neural networks aesthetic evaluation mould
Type is scored image (score range is 1-10 points).Convolutional neural networks aesthetic evaluation model is obtained by training, it is to avoid
The subjectivity and one-sidedness of artificial rule feature.
It should be noted that aesthetic evaluation model includes being not limited to use convolutional neural networks, other machines can be also used
Device learning method, for example, be limited Boltzmann machine, depth confidence network.The influence photo aesthetics that aesthetic evaluation model learning is arrived
Factor includes scene composition, brightness, contrast, colour temperature, saturation degree, bloom, shade, Y-PSNR etc..
In the step S4, the aesthetics scoring of statistics all photos of photograph album carries out quantization using respectively mode and is divided into five
Level, user search is supplied as Checking label.
It should be noted that the automatic grading method and system of the smart machine photograph album photo of the present invention can also be set to intelligence
Standby camera live view image is scored, available for suggestion of taking pictures, its sorting technique and smart machine photograph album photo oneself
Dynamic stage division is identical.
Involved smart machine includes being not limited to PC, smart mobile phone, tablet personal computer, Yi Jiqi in the present invention
He has the equipment of data processing function.Be classified photo origin includes and is not limited to smart machine photograph album, and equipment also can be used
Camera live view image.Scene classification classification includes and is not limited to landscape, portrait, night scene, building, animal, plant, dynamic
State, static state, nine classifications of backlight.Scene classification result can as convolutional neural networks aesthetic evaluation model input parameter,
Also it can use and individually set up its corresponding convolutional neural networks model for each scene classification.Aesthetic evaluation model is included simultaneously
It is not limited to use convolutional neural networks model, can also uses other deep learning models, for example, is limited Boltzmann machine, depth and puts
Communication network.Quantization modulation quantity includes being not limited to Pyatyi.Quantization modulation mode includes being not limited to using respectively mode, also may be used
Using LOG modes or exponential manner.
This method embodiment realizes the aesthetics classification to photo, wherein, it is the phase in smart machine that image, which obtains source,
Volume photo, or be intelligent video camera head live view image, and by carrying out scene classification, lifting aesthetics to photograph album photo in advance
Accuracy is evaluated, using convolutional neural networks aesthetic evaluation model, it is to avoid the subjectivity and one-sidedness of artificial rule feature, we
The scope that method and system can be applicable is wide, can be generally applicable in smart machine.
Embodiments of the invention are the foregoing is only, are not intended to limit the invention, for those skilled in the art
For member, the present invention can have various modifications and variations.Any modification within the spirit and principles of the invention, being made,
Equivalent substitution, improvement etc., should be included within scope of the presently claimed invention.
Claims (10)
1. a kind of photo automatic grading method, it is characterised in that comprise the following steps:
Obtain smart machine photograph image;
Aesthstic scoring is carried out to the photograph image, grade and the display of the photograph image are obtained according to the aesthetics scoring.
2. photo automatic grading method as claimed in claim 1, it is characterised in that aesthstic scoring is carried out to the photograph image
Comprise the following steps:
The photograph image is input in default aesthetic evaluation model, the aesthetics scoring of the photograph image is obtained.
3. photo automatic grading method as claimed in claim 1, it is characterised in that commented carrying out aesthetics to the photograph image
/ preceding, it is further comprising the steps of:
Using default image scene classification algorithm, the photograph image is identified and analyzed, the photograph image is obtained
The classification results of affiliated scene;
Further, aesthetics scoring is carried out to the photograph image to comprise the following steps:
The classification results of the photograph image and the affiliated scene of the photograph image are input to default aesthetic evaluation model
In, obtain the aesthetics scoring of the photograph image.
4. photo automatic grading method as claimed in claim 1, it is characterised in that the photograph image be in smart machine
The photograph image or smart machine live view photograph image of preservation.
5. photo automatic grading method as claimed in claim 4, it is characterised in that also include:
When the photograph image is the photograph image preserved in smart machine, according to the photo figure preserved in smart machine
The aesthetics scoring of picture, classifies, and show classification results to the photograph image.
6. a kind of photo self-grading device, it is characterised in that including photograph image acquisition module, grade classification module:
The photograph image acquisition module, for obtaining smart machine photograph image;
The grade classification module, for carrying out aesthstic scoring to the photograph image, scores according to the aesthetics, obtains described
The grade of photograph image and display.
7. photo self-grading device as claimed in claim 6, it is characterised in that the grade classification module is used for:
The photograph image is input in default aesthetic evaluation model, the aesthetics scoring of the photograph image is obtained.
8. photo self-grading device as claimed in claim 6, it is characterised in that also including image scene classification module:
Described image scene classification module, for using default image scene classification algorithm, knows to the photograph image
Other and analysis, obtains the classification results of the affiliated scene of the photograph image;
The grade classification module is additionally operable to:
The classification results of the photograph image and the affiliated scene of the photograph image are input to default aesthetic evaluation model
In, obtain the aesthetics scoring of the photograph image.
9. photo self-grading device as claimed in claim 6, it is characterised in that the photograph image be in smart machine
The photograph image of preservation or the live view photograph image of smart machine.
10. photo self-grading device as claimed in claim 9, it is characterised in that also including sort module:
The sort module, when the photograph image is the photograph image preserved in smart machine, according in smart machine
The aesthetics scoring of the photograph image preserved, classifies, and show classification results to the photograph image.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710257193.2A CN107153838A (en) | 2017-04-19 | 2017-04-19 | A kind of photo automatic grading method and device |
PCT/CN2017/116059 WO2018192245A1 (en) | 2017-04-19 | 2017-12-14 | Automatic scoring method for photo based on aesthetic assessment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710257193.2A CN107153838A (en) | 2017-04-19 | 2017-04-19 | A kind of photo automatic grading method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107153838A true CN107153838A (en) | 2017-09-12 |
Family
ID=59793930
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710257193.2A Pending CN107153838A (en) | 2017-04-19 | 2017-04-19 | A kind of photo automatic grading method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107153838A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108198177A (en) * | 2017-12-29 | 2018-06-22 | 广东欧珀移动通信有限公司 | Image acquiring method, device, terminal and storage medium |
CN108596901A (en) * | 2018-05-03 | 2018-09-28 | 朱钢 | A kind of implementation method of intelligence test and appraisal real shooting photo imaging image quality |
WO2018192245A1 (en) * | 2017-04-19 | 2018-10-25 | 中国电子科技集团公司电子科学研究院 | Automatic scoring method for photo based on aesthetic assessment |
CN109218615A (en) * | 2018-09-27 | 2019-01-15 | 百度在线网络技术(北京)有限公司 | Image taking householder method, device, terminal and storage medium |
WO2019114147A1 (en) * | 2017-12-15 | 2019-06-20 | 华为技术有限公司 | Image aesthetic quality processing method and electronic device |
CN110060122A (en) * | 2019-03-16 | 2019-07-26 | 平安城市建设科技(深圳)有限公司 | Picture display method, device, equipment and computer readable storage medium |
CN110658965A (en) * | 2018-06-28 | 2020-01-07 | Tcl集团股份有限公司 | Photo selection method, device and terminal |
CN111008971A (en) * | 2019-12-24 | 2020-04-14 | 天津工业大学 | Aesthetic quality evaluation method of group photo image and real-time shooting guidance system |
CN111382295A (en) * | 2018-12-27 | 2020-07-07 | 北京搜狗科技发展有限公司 | Image search result sorting method and device |
CN113010723A (en) * | 2021-03-17 | 2021-06-22 | 维沃移动通信有限公司 | Electronic equipment, server control method and device |
CN114140655A (en) * | 2022-01-29 | 2022-03-04 | 深圳市中讯网联科技有限公司 | Image classification method and device, storage medium and electronic equipment |
CN115098449A (en) * | 2022-08-26 | 2022-09-23 | 荣耀终端有限公司 | File cleaning method and electronic equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102088539A (en) * | 2009-12-08 | 2011-06-08 | 浪潮乐金数字移动通信有限公司 | Method and system for evaluating pre-shot picture quality |
CN102576461A (en) * | 2009-09-25 | 2012-07-11 | 伊斯曼柯达公司 | Estimating aesthetic quality of digital images |
CN103218619A (en) * | 2013-03-15 | 2013-07-24 | 华南理工大学 | Image aesthetics evaluating method |
CN103248817A (en) * | 2012-02-13 | 2013-08-14 | 宏达国际电子股份有限公司 | Image capture method and mobile camera device thereof |
CN105678624A (en) * | 2014-11-18 | 2016-06-15 | 索尼公司 | Evaluation information generation device and method, electronic device and server |
-
2017
- 2017-04-19 CN CN201710257193.2A patent/CN107153838A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102576461A (en) * | 2009-09-25 | 2012-07-11 | 伊斯曼柯达公司 | Estimating aesthetic quality of digital images |
CN102088539A (en) * | 2009-12-08 | 2011-06-08 | 浪潮乐金数字移动通信有限公司 | Method and system for evaluating pre-shot picture quality |
CN103248817A (en) * | 2012-02-13 | 2013-08-14 | 宏达国际电子股份有限公司 | Image capture method and mobile camera device thereof |
CN103218619A (en) * | 2013-03-15 | 2013-07-24 | 华南理工大学 | Image aesthetics evaluating method |
CN105678624A (en) * | 2014-11-18 | 2016-06-15 | 索尼公司 | Evaluation information generation device and method, electronic device and server |
Non-Patent Citations (1)
Title |
---|
WEINING WANG 等: "A multi-scene deep learning model for image aesthetic evaluation", 《SIGNAL PROCESSING: IMAGE COMMUNICATION》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018192245A1 (en) * | 2017-04-19 | 2018-10-25 | 中国电子科技集团公司电子科学研究院 | Automatic scoring method for photo based on aesthetic assessment |
WO2019114147A1 (en) * | 2017-12-15 | 2019-06-20 | 华为技术有限公司 | Image aesthetic quality processing method and electronic device |
US11314988B2 (en) | 2017-12-15 | 2022-04-26 | Huawei Technologies Co., Ltd. | Image aesthetic processing method and electronic device |
CN108198177A (en) * | 2017-12-29 | 2018-06-22 | 广东欧珀移动通信有限公司 | Image acquiring method, device, terminal and storage medium |
CN108596901A (en) * | 2018-05-03 | 2018-09-28 | 朱钢 | A kind of implementation method of intelligence test and appraisal real shooting photo imaging image quality |
CN110658965A (en) * | 2018-06-28 | 2020-01-07 | Tcl集团股份有限公司 | Photo selection method, device and terminal |
CN109218615A (en) * | 2018-09-27 | 2019-01-15 | 百度在线网络技术(北京)有限公司 | Image taking householder method, device, terminal and storage medium |
CN111382295A (en) * | 2018-12-27 | 2020-07-07 | 北京搜狗科技发展有限公司 | Image search result sorting method and device |
CN111382295B (en) * | 2018-12-27 | 2024-04-30 | 北京搜狗科技发展有限公司 | Image search result ordering method and device |
CN110060122A (en) * | 2019-03-16 | 2019-07-26 | 平安城市建设科技(深圳)有限公司 | Picture display method, device, equipment and computer readable storage medium |
CN111008971A (en) * | 2019-12-24 | 2020-04-14 | 天津工业大学 | Aesthetic quality evaluation method of group photo image and real-time shooting guidance system |
CN113010723A (en) * | 2021-03-17 | 2021-06-22 | 维沃移动通信有限公司 | Electronic equipment, server control method and device |
CN114140655A (en) * | 2022-01-29 | 2022-03-04 | 深圳市中讯网联科技有限公司 | Image classification method and device, storage medium and electronic equipment |
CN115098449A (en) * | 2022-08-26 | 2022-09-23 | 荣耀终端有限公司 | File cleaning method and electronic equipment |
CN115098449B (en) * | 2022-08-26 | 2023-07-07 | 荣耀终端有限公司 | File cleaning method and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107153838A (en) | A kind of photo automatic grading method and device | |
CN111368893B (en) | Image recognition method, device, electronic equipment and storage medium | |
CN108960245B (en) | Tire mold character detection and recognition method, device, equipment and storage medium | |
US9898647B2 (en) | Systems and methods for detecting, identifying and tracking objects and events over time | |
CN109068056B (en) | Electronic equipment, filter processing method of image shot by electronic equipment and storage medium | |
CN110163076B (en) | Image data processing method and related device | |
CN103617432A (en) | Method and device for recognizing scenes | |
US9305208B2 (en) | System and method for recognizing offensive images | |
CN108492294B (en) | Method and device for evaluating harmony degree of image colors | |
GB2595558A (en) | Exposure defects classification of images using a neural network | |
CN110097616B (en) | Combined drawing method and device, terminal equipment and readable storage medium | |
CN106611015B (en) | Label processing method and device | |
CN108198177A (en) | Image acquiring method, device, terminal and storage medium | |
WO2020207203A1 (en) | Prospect data generation and application methods, related apparatus and system | |
CN103116754A (en) | Batch image segmentation method and batch image segmentation system based on recognition models | |
CN110298380A (en) | Image processing method, device and electronic equipment | |
CN104954678A (en) | Image processing method, image processing device and electronic equipment | |
JP6787831B2 (en) | Target detection device, detection model generation device, program and method that can be learned by search results | |
CN107943811A (en) | The dissemination method and device of content | |
CN107506362B (en) | Image classification brain-imitation storage method based on user group optimization | |
US10192131B2 (en) | Logo image indentification system | |
CN112418327A (en) | Training method and device of image classification model, electronic equipment and storage medium | |
CN112200844A (en) | Method, device, electronic equipment and medium for generating image | |
CN112839167B (en) | Image processing method, device, electronic equipment and computer readable medium | |
CN116095363A (en) | Mobile terminal short video highlight moment editing method based on key behavior recognition |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170912 |