CN103793697A - Identity labeling method of face images and face identity recognition method of face images - Google Patents
Identity labeling method of face images and face identity recognition method of face images Download PDFInfo
- Publication number
- CN103793697A CN103793697A CN201410053879.6A CN201410053879A CN103793697A CN 103793697 A CN103793697 A CN 103793697A CN 201410053879 A CN201410053879 A CN 201410053879A CN 103793697 A CN103793697 A CN 103793697A
- Authority
- CN
- China
- Prior art keywords
- face
- identity
- picture
- marked
- face images
- 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.)
- Granted
Links
Images
Abstract
The invention discloses an identity labeling method of face images and a face identity recognition method of the face images. The face identity recognition method includes the steps of (1) labeling the identities of the face images to be labeled: searching the face images similar to the face images and corresponding webpages, determining the identities of the face images according to the frequencies of appeared names in the returned webpages, detecting the identities of the face images respectively through a face technology platform and a face identity recognition model, and synthesizing the recognition results to determine the final identities of the face images and label the face images, (2) carrying out matching filtering on a set of face images belonging to the same names and the face images with the label results as the names in the step (1), (3) extracting feature vectors of the filtered identity labeled face images, training the labeled face images with a machine learning algorithm, and generating a face identity recognition model, and (4) as for two face images to the detected, extracting the feature vectors of the face images to judge whether the two face images belong to the same person or not through the face identity recognition model. According to the identity labeling method and the face identity recognition method, the labeling efficiency and the recognition effect are greatly improved.
Description
Technical field
The present invention relates to a kind of face identification method, relate in particular to a kind of identity mask method and face personal identification method of facial image, belong to image recognition technology field.
Background technology
Face recognition technology is used widely in each field at present, become a current study hotspot, such as the patent documentation of application number 201210313721.9, title " face identification method ", the patent documentation of application number 201210310643.7, title " a kind of face identification method and system thereof ".
Wherein, extraction and mark that face detects human face characteristic point in recognition methods are a requisite job, such as application number 201310115471.2, title " a kind of face automatic marking method and system " first detects face from the video intercepting, obtain the set of face picture, then filter out the set of face picture, simultaneously, obtain the hsv color histogram difference of consecutive frame picture, the lens edge detection algorithm of employing spatial color histogram carries out camera lens to be cut apart, to the face from consecutive frame, detect angle point in the target area of the first frame, and the method that uses local matching is by deferred these angle points next frame of giving, and upgrade accordingly, and statistical match number, according to the threshold value of coupling number, go on according to this and obtain face sequence.Then move detection module by lip and detect speaker and speaker not according to the lip of speaker in face sequence is moving, speaker, the content of speaking and the time three of speaking are integrated into rower and note; Finally, read in the face in each sequence, location one by one, then carry out affined transformation according to positioning result, and extract the grey scale pixel value near the fixed size border circular areas of the rear unique point of conversion, as this face characteristic.
Application number 200610096709.1; title " man face characteristic point positioning method in face identification system " also relates to the man face characteristic point positioning method in face identification system; utilize the statistical model of image gradient directional information; method by statistical reasoning is determined human face characteristic point; comprise the following steps: (1) definition and location human face characteristic point, utilize the direction definition of image gradient and location candidate's human face characteristic point; (2) in extraction step (1), the proper vector (3) of human face characteristic point is utilized a statistical model of having considered feature and the relativeness of human face characteristic point, adopt the method for statistical reasoning, mark human face characteristic point, thereby the position of definite human face characteristic point needing.
Face technology belongs to machine learning category, technology and system all need to experience data training process, a large amount of facial images are given to algorithm as input together with corresponding mark, thereby algorithm can go out corresponding model for practical application according to these training data automatic learnings.Because current method for detecting human face requires the characteristic attribute information requirements of detection more and more abundanter, generally obtain model of cognition by there being the facial image of mark to utilize machine learning algorithm to train, thereby numerous not facial images of mark are marked and identified.But effectively solved about the mask method of face identity, if simply remove to screen one by one mark by manual method, very consuming time. always
Summary of the invention
For problems of the prior art, the object of the present invention is to provide a kind of identity mask method of facial image and the recognition methods based on the large datacycle of face picture.
Technical scheme of the present invention is:
An identity mask method for facial image, the steps include:
1) search and the facial image of face picture analogies to be marked and corresponding webpage from image search engine;
2) the statistics frequency that occurs name in webpage of returning, and according to the identity of tentatively definite this face picture to be marked of this frequency;
3) adopt respectively face technology platform and face identification model to detect the identity of this face picture to be marked;
4) according to step 2), 3) recognition result determine the final identity of this face picture to be marked, mark the identity of this face picture to be marked.
Further, first extract face position and the key point information of face picture to be marked, by face location criteria to a standard format on the face.
Further, described face identification model is opened image by the N that belongs to same name of search and is compared between two the degree of confidence that the identity of face in picture belongs to same person; Then determine according to degree of confidence whether face picture identity to be marked is this name.
A face personal identification method for facial image, the steps include:
1) automatic data acquisition system obtains face picture and contextual information thereof from server;
2) data automatic marking system marks the identity of each the face picture to be marked obtaining; Wherein mask method is:
21) search and the facial image of face picture analogies to be marked and corresponding webpage from image search engine;
22) the statistics frequency that occurs name in webpage of returning, and according to the identity of tentatively definite this face picture to be marked of this frequency;
23) adopt respectively face technology platform and face identification model to detect the identity of this face picture to be marked;
24) according to step 22), 23) recognition result determine the final identity of this face picture to be marked, mark the identity of this face picture to be marked;
3) by the picture group sheet and step 2 that belongs to same name gathering in automatic data acquisition system) in annotation results be this name picture mates filtration, remove the face picture that does not belong to this name in this group;
4) extraction step 3) proper vector of each identity mark picture of retaining after filtering, the face picture training after automatic algorithms training system utilizes machine learning algorithm to identity mark, generates a face identification model;
5), for two facial images to be detected, extract its proper vector and utilize described face identification model to judge whether it belongs to same people.
Further, the method that described automatic data acquisition system obtains face picture and contextual information thereof from server is:
51) described server is according to the corresponding face picture file of name keyword search of input preservation;
52) calculate Hash codes, color histogram, context and the label information of each face picture file;
53) by each face picture with deposited that face picture carries out Hash codes and color histogram is compared, remove the image repeating;
54) end user's face detection algorithm module detecting step 53) process rear each face picture retaining, by face positional information
Be saved in database; Use the key point information on the face of face key point location algorithm location and be saved in database.
Further, step 21) first extract before face position and the key point information of face picture to be marked, by face location criteria to a standard format on the face.
As described in Figure 1, its detection method comprises following steps to detection system of the present invention:
1) automatic data acquisition system, automatically from search engine, social networks, and the photograph album class application background server of taking pictures constantly excavates the needed face data of learning algorithm and related context information;
2) data automatic marking system, by a small amount of manual intervention, the noise in automatic fitration image data, and utilize the needed face identity of contextual information automatic mining learning algorithm markup information;
3) automatic algorithms training system, is obtaining face data and identity markup information that automatic mining goes out, and this system is regularly sent into data automatically Algorithm Learning system and carried out Algorithm for Training, and after having trained, automatically structure can execution algorithm module;
4) the up-to-date algoritic module obtaining 3) can circulate and enter 2) subsystem, thereby help better to face identity mark.
Compared with prior art, good effect of the present invention is:
The present invention can realize facial image identity is carried out to automatic marking, has greatly improved the efficiency of facial image mark; Face identification method of the present invention can help to make full use of the advantage of large data, greatly promotes recognition effect.
Accompanying drawing explanation
Fig. 1. overall system schematic diagram;
Fig. 2. automatic data collection method schematic diagram;
Fig. 3. data automatic marking method schematic diagram;
Fig. 4. automatic algorithms training schematic diagram.
Embodiment
Below in conjunction with accompanying drawing, technology of the present invention is explained in further detail.
1) automatic data acquisition system (as shown in Figure 2)
A key condition that promotes each sport technique segment algorithm performance of face technology is the extensive face data that obtain better quality.Classic method is manually to build collection environment, organizes volunteer to gather facial image, the face data that artificial mark gathers, and such as the picture position of face, the image coordinate of face key point, the age of face, identity etc.Classic method gathers consuming time, and the data that collect are also very dull, such as all regional at one, or certain age bracket, under certain illumination condition, the view data of certain human face posture, its multifarious shortage cannot meet the Algorithm for Training requirement of high performance face technology.The appearance of search engine and internet provides the possibility of large data mining and utilization, and a large amount of name personal data can obtain by name key search very efficiently.On social networks and photograph album, also have the facial image data of a large amount of same persons, these all provide abundant face identity data source for promoting face recognition algorithms simultaneously.How utilizing these data boosting algorithm performances is also a problem requiring study at present.
For the problems referred to above, this method is used the collection of following steps robotization to excavate face data:
1. system is searched for name key word on search engine, and key word library obtains from all kinds of encyclopaedia data, such as physical culture, and name of performing art star etc.
2. system is downloaded the result images file that search engine provides automatically, be saved in a temporary file system, in file, part facial image data are the facial images that mate with the name of retrieving, remaining facial image does not belong to this name, need to take data automatic marking system, i.e. system 2) in describe step filter.
3. Hash codes (for example using MD5 algorithm) and color histogram data and context and the label information (as data source web, timestamp, keyword in context etc.) of the image file of downloading in calculation procedure 2, deposit database in, and set up index.
4. the data that obtain in pair step 3 are carried out duplicate removal processing: each pictures all will with database in the picture of having put in storage carry out the comparison of Hash codes and color histogram, remove the image repeating.
5. remaining picture after screening in step 4 is preserved to the distributed file system lasting into.
6. the face in the image of preserving in end user's face detection algorithm module detecting step 5, is saved in database by face positional information; Use the key point information on the face of face key point location algorithm module location and be saved in database.
7. final this system produces a distributed file system of having stored image file data and one and preserves the distributed data base of various faces and image primitive information.
2) data automatic marking system (as shown in Figure 3)
1. for the face picture producing in acquisition system, utilize face position that acquisition system step 6 produces, with key point information, image is preserved into in face location criteria to fixed size and position and facilitate subsequent step 4) in extract proper vector.
2. the facial image producing in uploading step 1 in third party's searching image search engine, search obtains the similar face picture source web page corresponding with it and is connected.In the results web page obtaining, analyze name key word, add up the frequency that each name key word occurs, its frequency statistics result is converted into degree of confidence with following formula and (supposes to have M name, wherein pi represents the frequency that i name occurs, Xi represents that i name is the degree of confidence of this facial image identity).
Xi=pi/(p1+p2+...＋ｐM)，
At third party's face technology API platform (with reference to http://www.skybiometry.com/Demo; Http:// www.lambdal.com/) in upload in step 1 facial image producing, obtain identification result, extract and return results the degree of confidence that the possible name identity listed (suppose that API returns to K possible name) and third party's face technology API platform provide.This degree of confidence is equally also that specific name is the degree of confidence of this facial image identity.
4. 2,3 result is used data which and the download name key word used that weighted mean obtains downloading in acquisition system to mate, thus the image data after being filtered.
Experiment shows, this method can obtain face identity labeled data very accurately.Results of property is in table 1.The performance figures that we have listed conventional manual mask method as a comparison.Classic method checks thereby whether each the face picture in download pictures mates download name key word used and filter out the picture meeting one by one.
Table 1 is identity mark Contrast on effect table
| ? | Manually mark | The method that the present invention proposes |
| Mark accuracy | 99.4% | 99.2% |
| Average every pictures label time | 12 seconds | 0.8 second |
3) automatic algorithms training system (as shown in Figure 4)
Obtaining labeling system 2) filter after facial image data, the proper vector that native system extracts each identity mark picture (can be used the LBP in open field, Gabor, any one proper vector such as HOG), automatic algorithms training system utilizes machine learning algorithm regularly to the face picture training after identity mark, generates a face identification model; Then thereby the data importing Algorithm for Training system that meets screening conditions is detected to the picture of inputting and whether belong to same person.Its concrete steps are as follows:
1. user is regularly according to demand by the face data volume of needs and screening conditions (such as image all derives from 10000 of internets famous person's search data of 2013, everyone 50 pictures) task queue database of typing.
2. the timing of automatic algorithms training system is read task from task queue database.
3. system is normalized into the needed storage format of this Algorithm for Training by the image in 2 and data according to the target algorithm in task.
4. system is trained the data upload after the normalization in 3 to learning training server, training objective be given a pair of facial image data algorithm module whether export this pair of people be same person, generate a face identification model; For the facial image of same name retrieval, extract its proper vector; Then utilize described face identification model to detect it, identify it and whether belong to same people.
The self-adaptation face machine learning algorithm training system based on large data that the present invention describes can, for the modules of face technology, detect including but not limited to face, face key point location, dividing property of face character (sex, age, race, expression etc.), and face identification.
Claims (6)
1. an identity mask method for facial image, the steps include:
1) search and the facial image of face picture analogies to be marked and corresponding webpage from image search engine;
2) the statistics frequency that occurs name in webpage of returning, and according to the identity of tentatively definite this face picture to be marked of this frequency;
3) adopt respectively face technology platform and face identification model to detect the identity of this face picture to be marked;
4) according to step 2), 3) recognition result determine the final identity of this face picture to be marked, mark the identity of this face picture to be marked.
2. the method for claim 1, is characterized in that first extracting face position and the key point information of face picture to be marked, by face location criteria to a standard format on the face.
3. method as claimed in claim 1 or 2, is characterized in that described face identification model opens image by the N that belongs to same name of search and compare between two the degree of confidence that the identity of face in picture belongs to same person; Then determine according to degree of confidence whether face picture identity to be marked is this name.
4. a face personal identification method for facial image, the steps include:
1) automatic data acquisition system obtains face picture and contextual information thereof from server;
2) data automatic marking system marks the identity of each the face picture to be marked obtaining; Wherein mask method is:
21) search and the facial image of face picture analogies to be marked and corresponding webpage from image search engine;
22) the statistics frequency that occurs name in webpage of returning, and according to the identity of tentatively definite this face picture to be marked of this frequency;
23) adopt respectively face technology platform and face identification model to detect the identity of this face picture to be marked;
24) according to step 22), 23) recognition result determine the final identity of this face picture to be marked, mark the identity of this face picture to be marked;
3) by the picture group sheet and step 2 that belongs to same name gathering in automatic data acquisition system) in annotation results be this name picture mates filtration, remove the face picture that does not belong to this name in this group;
4) extraction step 3) proper vector of each identity mark picture of retaining after filtering, the face picture training after automatic algorithms training system utilizes machine learning algorithm to identity mark, generates a face identification model;
5), for two facial images to be detected, extract its proper vector and utilize described face identification model to judge whether it belongs to same people.
5. method as claimed in claim 4, is characterized in that the method that described automatic data acquisition system obtains face picture and contextual information thereof from server is:
51) described server is according to the corresponding face picture file of name keyword search of input preservation;
52) calculate Hash codes, color histogram, context and the label information of each face picture file;
53) by each face picture with deposited that face picture carries out Hash codes and color histogram is compared, remove the image repeating;
54) end user's face detection algorithm module detecting step 53) process rear each face picture retaining, by face positional information
Be saved in database; Use the key point information on the face of face key point location algorithm location and be saved in database.
6. the method as described in claim 4 or 5, is characterized in that step 21) first extract before face position and the key point information of face picture to be marked, by face location criteria to a standard format on the face.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410053879.6A CN103793697B (en) | 2014-02-17 | 2014-02-17 | The identity mask method and face personal identification method of a kind of facial image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410053879.6A CN103793697B (en) | 2014-02-17 | 2014-02-17 | The identity mask method and face personal identification method of a kind of facial image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103793697A true CN103793697A (en) | 2014-05-14 |
| CN103793697B CN103793697B (en) | 2018-05-01 |
Family
ID=50669342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410053879.6A Active CN103793697B (en) | 2014-02-17 | 2014-02-17 | The identity mask method and face personal identification method of a kind of facial image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103793697B (en) |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103984738A (en) * | 2014-05-22 | 2014-08-13 | 中国科学院自动化研究所 | Role labelling method based on search matching |
| CN104091164A (en) * | 2014-07-28 | 2014-10-08 | 北京奇虎科技有限公司 | Face picture name recognition method and system |
| CN104281842A (en) * | 2014-10-13 | 2015-01-14 | 北京奇虎科技有限公司 | Face picture name identification method and device |
| CN104463177A (en) * | 2014-12-23 | 2015-03-25 | 北京奇虎科技有限公司 | Similar face image obtaining method and device |
| CN104537341A (en) * | 2014-12-23 | 2015-04-22 | 北京奇虎科技有限公司 | Human face picture information obtaining method and device |
| CN104778481A (en) * | 2014-12-19 | 2015-07-15 | 五邑大学 | Method and device for creating sample library for large-scale face mode analysis |
| CN104850600A (en) * | 2015-04-29 | 2015-08-19 | 百度在线网络技术（北京）有限公司 | Method and device for searching images containing faces |
| CN105138245A (en) * | 2015-09-30 | 2015-12-09 | 北京奇虎科技有限公司 | Deduplication processing method and device for screenshot pictures of intelligent terminal |
| CN105468760A (en) * | 2015-12-01 | 2016-04-06 | 北京奇虎科技有限公司 | Method and apparatus for labeling face images |
| CN105678622A (en) * | 2016-01-07 | 2016-06-15 | 平安科技（深圳）有限公司 | Analysis method and system for vehicle insurance claim-settlement photos |
| CN105979331A (en) * | 2015-12-01 | 2016-09-28 | 乐视致新电子科技（天津）有限公司 | Smart television data recommend method and device |
| CN106203294A (en) * | 2016-06-30 | 2016-12-07 | 广东微模式软件股份有限公司 | The testimony of a witness unification auth method analyzed based on face character |
| CN106327546A (en) * | 2016-08-24 | 2017-01-11 | 北京旷视科技有限公司 | Face detection algorithm test method and device |
| CN106326815A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技（杭州）有限公司 | Human face image recognition method |
| CN106503691A (en) * | 2016-11-10 | 2017-03-15 | 广州视源电子科技股份有限公司 | A kind of identity mask method of face picture and device |
| CN106548162A (en) * | 2016-11-24 | 2017-03-29 | 中译语通科技（北京）有限公司 | It is a kind of that the method with name human face data is automatically extracted from news pages |
| WO2017054442A1 (en) * | 2015-09-30 | 2017-04-06 | 腾讯科技（深圳）有限公司 | Image information recognition processing method and device, and computer storage medium |
| CN106649610A (en) * | 2016-11-29 | 2017-05-10 | 北京智能管家科技有限公司 | Image labeling method and apparatus |
| CN106844412A (en) * | 2016-11-02 | 2017-06-13 | 厦门中控生物识别信息技术有限公司 | A kind of human face data collection method and device |
| CN106934364A (en) * | 2017-03-09 | 2017-07-07 | 腾讯科技（上海）有限公司 | The recognition methods of face picture and device |
| CN108875453A (en) * | 2017-05-11 | 2018-11-23 | 北京旷视科技有限公司 | The method, apparatus and computer storage medium of face picture bottom library registration |
| WO2019015684A1 (en) * | 2017-07-21 | 2019-01-24 | 北京市商汤科技开发有限公司 | Facial image reduplication removing method and apparatus, electronic device, storage medium, and program |
| CN109583325A (en) * | 2018-11-12 | 2019-04-05 | 平安科技（深圳）有限公司 | Face samples pictures mask method, device, computer equipment and storage medium |
| CN109919754A (en) * | 2019-01-24 | 2019-06-21 | 北京迈格威科技有限公司 | A kind of data capture method, device, terminal and storage medium |
| CN110058407A (en) * | 2018-01-19 | 2019-07-26 | 尹寅 | A kind of intelligent glasses system shooting photos and videos |
| CN110084289A (en) * | 2019-04-11 | 2019-08-02 | 北京百度网讯科技有限公司 | Image labeling method, device, electronic equipment and storage medium |
| US10489637B2 (en) | 2014-12-23 | 2019-11-26 | Beijing Qihoo Technology Company Limited | Method and device for obtaining similar face images and face image information |
| WO2019237558A1 (en) * | 2018-06-14 | 2019-12-19 | 平安科技（深圳）有限公司 | Electronic device, picture sample set generation method, and computer readable storage medium |
| CN110825808A (en) * | 2019-09-23 | 2020-02-21 | 重庆特斯联智慧科技股份有限公司 | Distributed human face database system based on edge calculation and generation method thereof |
| CN110941736A (en) * | 2015-03-27 | 2020-03-31 | 华为技术有限公司 | Electronic photo display method and device and mobile equipment |
| CN113094538A (en) * | 2019-12-23 | 2021-07-09 | 中国电信股份有限公司 | Image retrieval method, device and computer-readable storage medium |
| CN115129921A (en) * | 2022-06-30 | 2022-09-30 | 重庆紫光华山智安科技有限公司 | Picture retrieval method and device, electronic equipment and computer-readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101668176A (en) * | 2009-09-25 | 2010-03-10 | 北京酷联天下科技有限公司 | Multimedia content-on-demand and sharing method based on social interaction graph |
| CN102055932A (en) * | 2009-10-30 | 2011-05-11 | 深圳Tcl新技术有限公司 | Method for searching television program and television set using same |
| CN102629275A (en) * | 2012-03-21 | 2012-08-08 | 复旦大学 | Face and name aligning method and system facing to cross media news retrieval |
| CN102648462A (en) * | 2009-11-18 | 2012-08-22 | 高通股份有限公司 | Methods and systems for managing electronic messages |
| CN102938065A (en) * | 2012-11-28 | 2013-02-20 | 北京旷视科技有限公司 | Facial feature extraction method and face recognition method based on large-scale image data |
-
2014
- 2014-02-17 CN CN201410053879.6A patent/CN103793697B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101668176A (en) * | 2009-09-25 | 2010-03-10 | 北京酷联天下科技有限公司 | Multimedia content-on-demand and sharing method based on social interaction graph |
| CN102055932A (en) * | 2009-10-30 | 2011-05-11 | 深圳Tcl新技术有限公司 | Method for searching television program and television set using same |
| CN102648462A (en) * | 2009-11-18 | 2012-08-22 | 高通股份有限公司 | Methods and systems for managing electronic messages |
| CN102629275A (en) * | 2012-03-21 | 2012-08-08 | 复旦大学 | Face and name aligning method and system facing to cross media news retrieval |
| CN102938065A (en) * | 2012-11-28 | 2013-02-20 | 北京旷视科技有限公司 | Facial feature extraction method and face recognition method based on large-scale image data |
Non-Patent Citations (5)
| Title |
|---|
| MATTHIEU GUILLAUMIN ET AL.: "Automatic Face Naming with Caotion-based Supervision", 《COMPUTER VISION AND PATTERN RECOGNITION,2008》 * |
| PHI THE PHAM ET AL.: "Cross-media alignment of names and faces", 《IEEE TRANSACTIONS ON MULTIMEDIA》 * |
| 付明: "基于GraphCuts的图像标注工具及管理系统的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 刘胜宇: "网络新闻图像中人脸标注技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 盛嘉: "找到你的脸_智能图片搜索技术", 《互联网天地》 * |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103984738A (en) * | 2014-05-22 | 2014-08-13 | 中国科学院自动化研究所 | Role labelling method based on search matching |
| CN104091164A (en) * | 2014-07-28 | 2014-10-08 | 北京奇虎科技有限公司 | Face picture name recognition method and system |
| CN104281842A (en) * | 2014-10-13 | 2015-01-14 | 北京奇虎科技有限公司 | Face picture name identification method and device |
| CN104778481A (en) * | 2014-12-19 | 2015-07-15 | 五邑大学 | Method and device for creating sample library for large-scale face mode analysis |
| CN104778481B (en) * | 2014-12-19 | 2018-04-27 | 五邑大学 | A kind of construction method and device of extensive face pattern analysis sample storehouse |
| CN104537341B (en) * | 2014-12-23 | 2016-10-05 | 北京奇虎科技有限公司 | Face picture information getting method and device |
| CN104463177A (en) * | 2014-12-23 | 2015-03-25 | 北京奇虎科技有限公司 | Similar face image obtaining method and device |
| CN104537341A (en) * | 2014-12-23 | 2015-04-22 | 北京奇虎科技有限公司 | Human face picture information obtaining method and device |
| US10489637B2 (en) | 2014-12-23 | 2019-11-26 | Beijing Qihoo Technology Company Limited | Method and device for obtaining similar face images and face image information |
| CN110941736A (en) * | 2015-03-27 | 2020-03-31 | 华为技术有限公司 | Electronic photo display method and device and mobile equipment |
| CN104850600A (en) * | 2015-04-29 | 2015-08-19 | 百度在线网络技术（北京）有限公司 | Method and device for searching images containing faces |
| CN106326815B (en) * | 2015-06-30 | 2019-09-13 | 芋头科技（杭州）有限公司 | A kind of facial image recognition method |
| CN106326815A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技（杭州）有限公司 | Human face image recognition method |
| CN105138245A (en) * | 2015-09-30 | 2015-12-09 | 北京奇虎科技有限公司 | Deduplication processing method and device for screenshot pictures of intelligent terminal |
| WO2017054442A1 (en) * | 2015-09-30 | 2017-04-06 | 腾讯科技（深圳）有限公司 | Image information recognition processing method and device, and computer storage medium |
| US10438086B2 (en) | 2015-09-30 | 2019-10-08 | Tencent Technology (Shenzhen) Company Limited | Image information recognition processing method and device, and computer storage medium |
| CN105138245B (en) * | 2015-09-30 | 2018-06-29 | 北京奇虎科技有限公司 | A kind of duplicate removal treatment method and device of intelligent terminal screenshot picture |
| CN105979331A (en) * | 2015-12-01 | 2016-09-28 | 乐视致新电子科技（天津）有限公司 | Smart television data recommend method and device |
| CN105468760A (en) * | 2015-12-01 | 2016-04-06 | 北京奇虎科技有限公司 | Method and apparatus for labeling face images |
| CN105468760B (en) * | 2015-12-01 | 2018-09-11 | 北京奇虎科技有限公司 | The method and apparatus that face picture is labeled |
| CN105678622A (en) * | 2016-01-07 | 2016-06-15 | 平安科技（深圳）有限公司 | Analysis method and system for vehicle insurance claim-settlement photos |
| CN106203294B (en) * | 2016-06-30 | 2019-05-03 | 广东微模式软件股份有限公司 | The testimony of a witness based on face character analysis unifies auth method |
| CN106203294A (en) * | 2016-06-30 | 2016-12-07 | 广东微模式软件股份有限公司 | The testimony of a witness unification auth method analyzed based on face character |
| CN106327546A (en) * | 2016-08-24 | 2017-01-11 | 北京旷视科技有限公司 | Face detection algorithm test method and device |
| CN106844412A (en) * | 2016-11-02 | 2017-06-13 | 厦门中控生物识别信息技术有限公司 | A kind of human face data collection method and device |
| CN106503691A (en) * | 2016-11-10 | 2017-03-15 | 广州视源电子科技股份有限公司 | A kind of identity mask method of face picture and device |
| CN106503691B (en) * | 2016-11-10 | 2019-12-20 | 广州视源电子科技股份有限公司 | Identity labeling method and device for face picture |
| CN106548162A (en) * | 2016-11-24 | 2017-03-29 | 中译语通科技（北京）有限公司 | It is a kind of that the method with name human face data is automatically extracted from news pages |
| CN106548162B (en) * | 2016-11-24 | 2019-03-29 | 中译语通科技股份有限公司 | A method of automatically extracting band name human face data from news pages |
| CN106649610A (en) * | 2016-11-29 | 2017-05-10 | 北京智能管家科技有限公司 | Image labeling method and apparatus |
| CN106934364A (en) * | 2017-03-09 | 2017-07-07 | 腾讯科技（上海）有限公司 | The recognition methods of face picture and device |
| CN108875453A (en) * | 2017-05-11 | 2018-11-23 | 北京旷视科技有限公司 | The method, apparatus and computer storage medium of face picture bottom library registration |
| US11132581B2 (en) | 2017-07-21 | 2021-09-28 | Beijing Sensetime Technology Development Co., Ltd | Method and apparatus for face image deduplication and storage medium |
| US11409983B2 (en) | 2017-07-21 | 2022-08-09 | Beijing Sensetime Technology Development Co., Ltd | Methods and apparatuses for dynamically adding facial images into database, electronic devices and media |
| WO2019015682A1 (en) * | 2017-07-21 | 2019-01-24 | 北京市商汤科技开发有限公司 | Dynamic facial image warehousing method and apparatus, electronic device, medium, and program |
| WO2019015684A1 (en) * | 2017-07-21 | 2019-01-24 | 北京市商汤科技开发有限公司 | Facial image reduplication removing method and apparatus, electronic device, storage medium, and program |
| CN110058407A (en) * | 2018-01-19 | 2019-07-26 | 尹寅 | A kind of intelligent glasses system shooting photos and videos |
| WO2019237558A1 (en) * | 2018-06-14 | 2019-12-19 | 平安科技（深圳）有限公司 | Electronic device, picture sample set generation method, and computer readable storage medium |
| CN109583325A (en) * | 2018-11-12 | 2019-04-05 | 平安科技（深圳）有限公司 | Face samples pictures mask method, device, computer equipment and storage medium |
| CN109583325B (en) * | 2018-11-12 | 2023-06-27 | 平安科技（深圳）有限公司 | Face sample picture labeling method and device, computer equipment and storage medium |
| CN109919754A (en) * | 2019-01-24 | 2019-06-21 | 北京迈格威科技有限公司 | A kind of data capture method, device, terminal and storage medium |
| CN110084289A (en) * | 2019-04-11 | 2019-08-02 | 北京百度网讯科技有限公司 | Image labeling method, device, electronic equipment and storage medium |
| CN110084289B (en) * | 2019-04-11 | 2021-07-27 | 北京百度网讯科技有限公司 | Image annotation method and device, electronic equipment and storage medium |
| CN110825808A (en) * | 2019-09-23 | 2020-02-21 | 重庆特斯联智慧科技股份有限公司 | Distributed human face database system based on edge calculation and generation method thereof |
| CN113094538A (en) * | 2019-12-23 | 2021-07-09 | 中国电信股份有限公司 | Image retrieval method, device and computer-readable storage medium |
| CN115129921A (en) * | 2022-06-30 | 2022-09-30 | 重庆紫光华山智安科技有限公司 | Picture retrieval method and device, electronic equipment and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103793697B (en) | 2018-05-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103793697A (en) | Identity labeling method of face images and face identity recognition method of face images | |
| CN103824053B (en) | The sex mask method and face gender detection method of a kind of facial image | |
| WO2020224424A1 (en) | Image processing method and apparatus, computer readable storage medium, and computer device | |
| CN109034159B (en) | Image information extraction method and device | |
| CN107169049B (en) | Application tag information generation method and device | |
| US10755086B2 (en) | Picture ranking method, and terminal | |
| CN106560810B (en) | Searching using specific attributes found in images | |
| US9436682B2 (en) | Techniques for machine language translation of text from an image based on non-textual context information from the image | |
| Zamberletti et al. | Text localization based on fast feature pyramids and multi-resolution maximally stable extremal regions | |
| CN106767812A (en) | A kind of interior semanteme map updating method and system based on Semantic features extraction | |
| CN103824052A (en) | Multilevel semantic feature-based face feature extraction method and recognition method | |
| CN107679070B (en) | Intelligent reading recommendation method and device and electronic equipment | |
| US9984304B2 (en) | Method and system for recognizing user activity type | |
| CN109426831B (en) | Image similarity matching and model training method and device and computer equipment | |
| US20130343618A1 (en) | Searching for Events by Attendants | |
| CN109753853A (en) | One kind being completed at the same time pedestrian detection and pedestrian knows method for distinguishing again | |
| JP5836779B2 (en) | Image processing method, image processing apparatus, imaging apparatus, and program | |
| Taverriti et al. | Real-time wearable computer vision system for improved museum experience | |
| CN109753962A (en) | Text filed processing method in natural scene image based on hybrid network | |
| CN112328833A (en) | Label processing method and device and computer readable storage medium | |
| CN108959664A (en) | Distributed file system based on picture processor | |
| CN113743251B (en) | Target searching method and device based on weak supervision scene | |
| CN105512155A (en) | Device and method for multi-layer semantic image retrieval | |
| CN105095215B (en) | Information acquisition device, method and server | |
| CN103198117B (en) | Content-based image spurious correlation method for reordering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |