CN101706872A - Universal open type face identification system - Google Patents
Universal open type face identification system Download PDFInfo
- Publication number
- CN101706872A CN101706872A CN200910199356A CN200910199356A CN101706872A CN 101706872 A CN101706872 A CN 101706872A CN 200910199356 A CN200910199356 A CN 200910199356A CN 200910199356 A CN200910199356 A CN 200910199356A CN 101706872 A CN101706872 A CN 101706872A
- Authority
- CN
- China
- Prior art keywords
- face
- database
- module
- people
- recognition
- 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
Images
Abstract
The invention relates to a universal open type face identification system which abstracts a related data in a face identification algorithm into a database data by introducing a backstage database support, adopts modularization and layering design and uses the backstage database as a bridge to perform the functions of collecting face samples, managing a face identification data, training a face classifier, guiding in a standard face database, testing for static picture face identification, testing for dynamic real-time face identification, generating a testing report, etc. Each module not only can work independently but also can work with other modules to finish tasks such as testing, real-time identification, etc. The invention can perform different face identification algorithms under an open type universal frame system, can finish face identification tasks in different databases and under different conditions, and can provide a reference model for the other face identification system.
Description
Technical field
The present invention relates to a kind of general open type face identification system, introduce the support of database, with versatility, open and distributed is design object, finish various recognition of face tasks by each functional module independence or collaborative work, for the design of practical face identification system provides with reference to prototype.Be mainly used in the face identification system design, the face recognition algorithms research field.
Background technology
The development through about 40 years is studied in recognition of face, detect and face tracking at people's face, the detection of human face characteristic point and demarcation, face characteristic is described and feature extraction, every field such as face characteristic classification, the researchist has launched extensive and deep research, various theories, various algorithms emerge in an endless stream, and have also reached certain degree of ripeness on the development technique of utility system simultaneously, therefore since later stage nineteen nineties, some recognition of face business systems have appearred successively.For the recognition of face business system of a maturation, not only need the support of good hardware platform, software systems and core algorithm are even more important.Simultaneously Automatic face recognition is the process of a complexity, from the collection of video flowing up to the recognition result that finally obtains, the middle processing that needs the many steps of experience, so the expression of data between each step, it is particularly crucial that computing and transmission seem.
Before releasing commercial system, face identification system need carry out various deep tests, in order to guarantee the validity of core recognizer, the researcher of face recognition algorithms is by test and relatively come assessment algorithm to seem particularly important, particularly under the situation of considering factors vary such as ambient lighting, human face posture, people's face accessories, human face expression, assessment face recognition algorithms rapidly and efficiently under static state or under using in real time effect be unusual difficulty.
Find that by prior art documents for the test of face recognition algorithms, most researchers all realizes by oneself building test platform at present.Existing general open face recognition algorithms test macro seldom.
U.S. Colorado State University once developed Face Identification EvaluationSystem, this system provides four kinds of basic face recognition algorithms (Eigenfaces, Combination PCA andLDA, Bayesian Intrapersonal/Extrapersoanl Image Difference Classier, Elastic Bunch Graph Matching), and can obtain the test result of standard faces storehouse FERET (Face RecognitionTechnology) on above-mentioned four kinds of algorithms, but this system adopts text mode to preserve experimental data, read-write efficiency is lower, and this system extension is very poor, and the user is difficult to the face recognition algorithms embedding of oneself is tested.The FRGC (Face Recognition Grand Challenge) that is presided over exploitation by America NI ST (National Institute of Standards and Technology) is that academia generally uses a cover face recognition algorithms evaluating system (Overview of the Face Recognition Grand Challenge, IEEEConference on Computer Vision and Pattern Recognition 2005), this system is primarily aimed at the high-resolution facial image, the test of three-dimensional face and facial image pre-service human face recognizer, the user can embed evaluating system to the face recognition algorithms of oneself easily and fast and test, experimental data is with the XML stored in file format, accelerated read-write efficiency, but this system only supports the FRGC face database, do not support other standard faces databases, and said system can only test the image-based face recognition algorithms, can't carry out the test of video-based face recognition algorithms.
Summary of the invention
The objective of the invention is at the deficiencies in the prior art, a kind of general open type face identification system is proposed, compatible as much as possible various face recognition algorithms, the recognition of face platform that satisfies test in early stage and practical application simultaneously can be provided, thereby provide with reference to prototype for the design of practical face identification system.
For achieving the above object, the present invention makes full use of the advantage of database on the management mass data, by introducing the database support, with related data in the face recognition algorithms abstract be database data, adopting the design of modularization and stratification, is bridge with the database, realizes the collection of people's face sample, the management of recognition of face data, the training of people's face sorter, the importing in standard faces storehouse, static images recognition of face test, dynamic real-time recognition of face test generates a series of functions such as test report.The realization corresponding function that works alone that each module both can distribute can co-operation be finished tasks such as test and Real time identification again.Under open general frame system, finish the recognition of face task of different face recognition algorithms under disparate databases, different situations, and the design that can be other recognition of face utility systems provides reference model.
General open type face identification system of the present invention comprises that database, video acquisition module, people's face sample collection module, standard faces database data import module, people's face sorter training module, dynamic real-time recognition of face test module, static images face recognition module, database management module and test report generation module.
Described video acquisition module links to each other with the dynamic real-time face recognition module with people's face sample collection module, respectively video flowing is imported people's face sample collection module and dynamic real-time face recognition module;
Described people's face sample collection module links to each other with database, and the data of gathering in the video flowing are carried out people's face detect and the facial image standardization, and with the sample information input database after the standardization;
Described standard faces database data imports module and links to each other with database, and people's face sample information that will read from the standard faces storehouse deposits database in;
Described people's face sorter training module links to each other with database, reads the sample information that people's face sample collection module or standard faces database data import the module input from database, trains, and will train the characteristic of division input database that extracts;
Described dynamic real-time face recognition module links to each other with database, reads the dynamic real-time people face picture feature information of video flowing, again with database in the characteristic of division that trains mate and discern, deposit recognition result in database;
Described static images face recognition module links to each other with database, the characteristic of division that trains in the static person face picture that reads and the database is mated and discerns, and deposits recognition result in database;
Described database management module links to each other with database, and the information that has in the database is put in order modification, stores back in the database again;
Described test report generation module links to each other with database, reads the information relevant with recognition result from database, generates test report output.
General open type face identification system of the present invention has versatility, opening, distributed characteristics, support by database, various recognition of face tasks are finished in work that each module is independent or collaborative, thereby are the reference that supplies a model of real-time face recognition system.
Described versatility comprises three layers of implication:
One, compatible as much as possible existing more popular face recognition algorithms, making it need not transform or only pass through function package just can embed in the system architecture of the present invention, promptly come out the predicable of different face recognition algorithms is abstract, realize by unified module or interface;
Two, the platform that utilizes system of the present invention to provide, can satisfy the dual needs of the test and the practical application of face recognition algorithms, even certain face recognition algorithms can reach good effect when test phase, then do not need to change or through very little change, just practical application can be directly used in, the construction cycle of testing practical application can be shortened like this;
Three, be applicable to simultaneously based on image face identification method (as the ratio equity of photo similarity) and based on the real-time face recognition methods (as real-time video monitoring etc.) of video, different input patterns (static images and real-time video flowing) promptly is provided.
Described open implication has two:
One, Kai Fangxing model, system carries out abstract to each key element of each necessary process of recognition of face; According to its abstract primitive of functional definition of each module, and do not stipulate the realization details of each module;
Two, the open system framework is realized, in the implementation procedure of system framework, has guaranteed that the object of each primitive in the encapsulation system has open design; Reasonable definition the interface of each object, enable to carry out interface and expand.
The described distributed two layers of meaning that comprises:
One, each functional module of system can independent distribution in (on for example same PC or on the server) on the same hardware platform, finish relatively independent separately function, and can finish whole recognition of face task by collaborative work;
Two, each functional module of system can independent distribution on different hardware platforms (different PCs or embedded platform in as LAN, or Internet goes up different main frames and terminal etc.), to satisfy different application demands.
Description of drawings
Fig. 1 is system structural framework figure of the present invention.
Fig. 2 is the identification process figure of system framework of the present invention.
Embodiment
Below in conjunction with accompanying drawing and specific embodiment technical scheme of the present invention is described in further detail.
The one-piece construction framework of open type face identification system of the present invention is seen Fig. 1.In order to embody versatility, open and distributed design object, system adopts distributed modular design, and each module is a bridge with the database, by the storehouse that reads and writes data, realizes data interaction, finishes the recognition of face task jointly.
As shown in Figure 1, general open type face identification system of the present invention comprises that database, video acquisition module, people's face sample collection module, database management module, people's face sorter training module, standard faces database data import module, static images face recognition module, dynamic real-time recognition of face test module and test report generation module.Video acquisition module links to each other with the dynamic real-time face recognition module with people's face sample collection module, respectively video flowing is imported people's face sample collection module and dynamic real-time face recognition module; People's face sample collection module links to each other with database, with the data input base of gathering in the video flowing; People's face sorter training module links to each other with database, reads people's face information from database, and with the sorter input database that trains; The dynamic real-time face recognition module links to each other with database with the static images face recognition module, reads characteristic information and discern from database; The standard faces database data imports module and links to each other with database with the standard faces storehouse, reads people's face from the standard faces storehouse, deposits people's face information in database again; Database management module links to each other with database, and the information in the reading database is put modification in order, stores back in the database again; Test report generation module links to each other with database, and the corresponding information arrangement of reading the identification situation from database generates test report output.
When system carried out the sample collection of people's face, video acquisition module was imported video flowing into people's face sample collection module, and this module is carried out people's face and detected and the facial image standardisation process, and with the sample information input database after the standardization;
When system carried out the importing of standard faces storehouse, the standard faces storehouse imported and obtains people's face sample after module is provided with partial parameters from the standard faces storehouse, and deposits database in;
When system carries out the training of people's face sorter, people's face sorter training module at first is provided with the part parameter relevant with training, from database, read people's face sample information that people's face sample collection module or standard faces storehouse import the module input then, train, will train the characteristic of division that extracts again and deposit database in;
When system carries out recognition of face, two kinds of people's face picture acquisition methods are arranged, a kind of is to gather video information from video flowing to be transferred to the dynamic real-time face recognition module, intercepting people face picture in this module, and a kind of is directly to read static person face picture from the static images face recognition module.Obtain after people's face picture, the characteristic of division that these two identification modules train sorter in face characteristic information in the picture and the database mates and discerns, and deposits recognition result in database.
Database management module carries out reconditioning to data all in the database, and last recognition result is exported by test report generation module.
Modularization is adopted in the design implementation of total system, and to embody following advantage: one, each functions of modules is relatively independent, can realize distributed design philosophy; Two, each module can be independent of outside the total system framework, realizes function corresponding, when independent module changes or during function upgrading, can not impact other modules and total system; But three, each module stand-alone development not only is convenient to debugging, reduces development difficulty, simultaneously can co-development, accelerate development progress.
Below in conjunction with Fig. 1, the concrete enforcement of each functional module of the present invention is described.
● this module of video acquisition module realizes the real-time collection of video flowing by VFW (Video For Windows) and camera or video acquisition cartoon letters.This module can be used different video acquisition modes according to different cameras or video frequency collection card.After this module collects video information, it is transferred to people's face sample collection module and dynamic real-time face recognition module.The compatible simultaneously several different main flow video acquisition mode now of the present invention comprises the USB digital camera, PCI video frequency collection card+simulation camera, USB video frequency collection card+simulation camera, PC104 video frequency collection card+simulation camera.
● people's face samples pictures of the training need some of people's face sample collection module recognition of face sorter, the video information that this module receiver, video acquisition module imports into can be gathered the people's face samples pictures that is applicable to recognition of face automatically.This module has people's face measuring ability simultaneously, can detect whether there is people's face in every frame video image, and the people's face quantity, position and the size that exist.When in video image, detecting people's face, this module can locate automatically people's face the principal character point (as eyes, eyebrow, nose, face etc.), and according to the position of these unique points, the standardization of finishing facial image is (as rotation, convergent-divergent is sheared in translation, pre-service, illiteracy plate etc.), finally obtain being used for people's face sample of training of human face sorter, and deposit these sample informations in database.
● the standard faces database data imports in the module standard face database thousands of facial images, and it is obviously unrealistic to handle these people's face pictures by the mode of craft, so standard faces database data importing module is essential.This module can will be used to test the data importing database of the universal standard face database of face recognition algorithms performance.General standard faces database comprises different test set and training set, in each set thousands of or tens thousand of people's face pictures are arranged generally, this module is according to the different attribute of people's face sample, the attribute of samples pictures is set automatically, thereby realize the classification of sample, and deposit people's face sample information in database.
● the core algorithm of people's face sorter training module recognition of face is embodied in the training of sorter, people's face sorter training module can be provided with different classifier parameters according to different algorithms, training different people face sorter. this module is tissue training's sample (comprise and selecting manually and automated randomized selection) efficiently, and can respective filter be set according to the attribute of samples pictures, select different attribute (as expression, age, illumination, attitude, sex, accessories etc.) people's face samples pictures is trained different people's face sorters, to satisfy face recognition algorithms in expression, age, illumination, attitude, the application when extraneous factors such as accessories change. this module reads people's face sample collection module from database or the standard faces database data imports the sample information that module is imported, train, deposit the platform database automatically in by the people's face characteristic of division that extracts after this module training.
● dynamic real-time face recognition module dynamic real-time face recognition module external camera collection to video flowing in, detect dynamic real-time people face picture feature information, obtain the facial image sample that is suitable for testing, again with database in people's face characteristic of division of training mate and discern, and depositing recognition result in database, dynamic real-time is finished recognition of face.
● some recognition of face task of static images face recognition module, the identity of portrait in the photo is judged in requirement according to given static images, the static images face recognition module provides the input interface of static images, the characteristic of division that trains in the static person face picture that reads and the database is mated and discern, deposit recognition result in database.
● the mass data of database management module database need manage, and can manage the various recognition of face data that relate in the database by database management module.This module can be added, and deletion is revised, and operations such as backup realize the personnel to database, the maintenance of data such as people's face samples pictures, face characteristic, people's face characteristic of division.All information of revising through the database management module arrangement still store back in the database.
● the test report generation module face recognition algorithms need be through the test of a large amount of people's face samples, and test report is improved algorithm to the developer of algorithm research person or utility system and had directive significance.Test report generation module can read the information relevant with recognition result from database, generate test report output.This module can be according to test result, the performance index that count face recognition algorithms are (as discrimination, false rejection rate, false acceptance rate etc.), and can generate the response curve chart, so that the comparison of different face recognition algorithms, thus the more superior recognizer of relative performance obtained, in real system, use.
Database is the center of whole open type face identification system, not only all data relevant with the recognition of face task all are stored in the database, the more important thing is the communications and data exchange between each functional module, all by data base read-write is finished, therefore, database has been taken on the role of " bridge ", and each functional module is linked to be an organic whole, and collaborative work is to finish the recognition of face task.The data that relate to recognition of face comprise personal information (numbering, name, sex, age etc.), people's face samples pictures information (numbering, path, picture format, dimension of picture, picture attribute, as light conditions, human face expression, human face posture, people's face accessories etc., picture acquisition time etc.), face characteristic information (numbering, feature number, picture numbering, personnel's numbering, the dimension of feature, characteristic etc.), people's face sorter (characteristic of division) information (numbering, comprise number, the dimension of sorter, classifier data etc.), training set information (lists of persons information, picture list information etc.), test set information (lists of persons information, picture list information etc.).
The present invention can adopt Microsoft SQL Server 2000 as database, builds whole open type face identification system framework.
The identification process of open type face identification system of the present invention is seen Fig. 2.The realization of total system roughly is divided into following four layers:
One, people's face sample input layer.Read in training personnel selection face sample or test personnel selection face sample by dynamic video or static images method
Two, pretreatment layer.People's face detects, and the standardization of face characteristic point location and location and facial image all is classified as pretreatment layer, behind this layer of every two field picture or static person image pattern picture process, is output as the standard faces image that is suitable for recognition of face in the video flowing;
Three, sorter training layer.Sorter training layer reads the sample of training usefulness, extracts the stronger feature of classification capacity in the sample.
Four, identification and test layer.This layer is realized identification and test assignment, when test sample book enters, reads the feature that sorter training layer trains, by characteristic matching output recognition result;
Five, interpretation of result and output layer. this layer finished the final step of recognition of face task, and the result with test analyzes to last layer identification, generates recognition result or test report etc.
The image of every frame video flowing or static images are finished the recognition of face task the most at last through above-mentioned five layers or wherein which floor.
Claims (1)
1. a general open type face identification system is characterized in that comprising that database, video acquisition module, people's face sample collection module, standard faces database data import module, people's face sorter training module, dynamic real-time recognition of face test module, static images face recognition module, database management module and test report generation module;
Described video acquisition module links to each other with the dynamic real-time face recognition module with people's face sample collection module, respectively video flowing is imported people's face sample collection module and dynamic real-time face recognition module;
Described people's face sample collection module links to each other with database, and the data of gathering in the video flowing are carried out people's face detect and the facial image standardization, and with the sample information input database after the standardization;
Described standard faces database data imports module and links to each other with database, and people's face sample information that will read from the standard faces storehouse deposits database in;
Described people's face sorter training module links to each other with database, reads the sample information that people's face sample collection module or standard faces database data import the module input from database, trains, and will train the characteristic of division input database that extracts;
Described dynamic real-time face recognition module links to each other with database, reads the dynamic real-time people face picture feature information of video flowing, again with database in the characteristic of division that trains mate and discern, deposit recognition result in database;
Described static images face recognition module links to each other with database, the characteristic of division that trains in the static person face picture that reads and the database is mated and discerns, and deposits recognition result in database;
Described database management module links to each other with database, and the information that has in the database is put in order modification, stores back in the database again;
Described test report generation module links to each other with database, reads the information relevant with recognition result from database, generates test report output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910199356A CN101706872A (en) | 2009-11-26 | 2009-11-26 | Universal open type face identification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910199356A CN101706872A (en) | 2009-11-26 | 2009-11-26 | Universal open type face identification system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101706872A true CN101706872A (en) | 2010-05-12 |
Family
ID=42377095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910199356A Pending CN101706872A (en) | 2009-11-26 | 2009-11-26 | Universal open type face identification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101706872A (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102004899A (en) * | 2010-11-03 | 2011-04-06 | 无锡中星微电子有限公司 | Human face identifying system and method |
| CN103279740A (en) * | 2013-05-15 | 2013-09-04 | 吴玉平 | Method and system for accelerating intelligent monitoring human face identification by utilizing dynamic database |
| CN103310190A (en) * | 2012-05-16 | 2013-09-18 | 清华大学 | Facial image sample acquiring and optimizing method based on heterogeneous active vision network |
| CN104375892A (en) * | 2014-11-14 | 2015-02-25 | 广东欧珀移动通信有限公司 | Method and device capable of achieving face recognition through intelligent and quick start and mobile terminal |
| WO2016184276A1 (en) * | 2015-05-20 | 2016-11-24 | 腾讯科技（深圳）有限公司 | Evaluation method and evaluation device for facial key point positioning result |
| CN107181766A (en) * | 2017-07-25 | 2017-09-19 | 湖南中迪科技有限公司 | The management-control method and device of log-on message |
| CN107241197A (en) * | 2017-07-25 | 2017-10-10 | 湖南中迪科技有限公司 | Password management-control method, device and password management and control device |
| CN107292841A (en) * | 2017-06-16 | 2017-10-24 | 石福荣 | Medelling image processing techniques |
| CN107566907A (en) * | 2017-09-20 | 2018-01-09 | 广东欧珀移动通信有限公司 | video clipping method, device, storage medium and terminal |
| CN107679448A (en) * | 2017-08-17 | 2018-02-09 | 平安科技（深圳）有限公司 | Eyeball action-analysing method, device and storage medium |
| CN108875474A (en) * | 2017-07-18 | 2018-11-23 | 北京旷视科技有限公司 | Assess the method, apparatus and computer storage medium of face recognition algorithms |
| CN108874657A (en) * | 2017-07-18 | 2018-11-23 | 北京旷视科技有限公司 | The method, apparatus and computer storage medium that recognition of face host is tested |
| CN109558812A (en) * | 2018-11-13 | 2019-04-02 | 广州铁路职业技术学院（广州铁路机械学校） | The extracting method and device of facial image, experience system and storage medium |
| CN109656800A (en) * | 2017-10-10 | 2019-04-19 | 百度在线网络技术（北京）有限公司 | Test method, device, terminal and the storage medium of image recognition application |
| CN109684498A (en) * | 2018-12-21 | 2019-04-26 | 北京贝思科技术有限公司 | Operation method, general-purpose platform and the storage medium of image analysis algorithm model |
| WO2019105285A1 (en) * | 2017-11-28 | 2019-06-06 | 腾讯科技（深圳）有限公司 | Facial attribute recognition method, electronic device, and storage medium |
| CN110097007A (en) * | 2019-04-30 | 2019-08-06 | 福建威盾科技集团有限公司 | A kind of method and device for integrating a variety of face recognition engines |
| CN110287781A (en) * | 2019-05-17 | 2019-09-27 | 江苏大学 | Recognition of face and speech synthesis emerging system |
| CN110309337A (en) * | 2018-03-14 | 2019-10-08 | 广州弘度信息科技有限公司 | A kind of centrally stored method and device of characteristic value for plurality of target recognizer |
| 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 |
| WO2020056902A1 (en) * | 2018-09-20 | 2020-03-26 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing mouth image |
| CN110956129A (en) * | 2019-11-28 | 2020-04-03 | 重庆中星微人工智能芯片技术有限公司 | Method, apparatus, device and medium for generating face feature vector |
| CN111275023A (en) * | 2020-03-19 | 2020-06-12 | 中国人民解放军国防科技大学 | Push-up test system based on face recognition and human body posture estimation |
| CN111526290A (en) * | 2017-11-08 | 2020-08-11 | Oppo广东移动通信有限公司 | Image processing method, device, terminal and storage medium |
| CN111782835A (en) * | 2020-06-30 | 2020-10-16 | 公安部第三研究所 | Face test database management system and method for face recognition equipment detection |
| CN112634520A (en) * | 2020-12-12 | 2021-04-09 | 上海应用技术大学 | Protection material distribution system based on face recognition technology |
| CN112733717A (en) * | 2021-01-11 | 2021-04-30 | 广州市金其利信息科技有限公司 | Method for optimizing face recognition based on face attributes |
| CN113177489A (en) * | 2021-05-07 | 2021-07-27 | 艾拉物联网络(深圳)有限公司 | High-precision portrait recognition method and system for security monitoring |
-
2009
- 2009-11-26 CN CN200910199356A patent/CN101706872A/en active Pending
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102004899A (en) * | 2010-11-03 | 2011-04-06 | 无锡中星微电子有限公司 | Human face identifying system and method |
| CN102004899B (en) * | 2010-11-03 | 2012-09-26 | 无锡中星微电子有限公司 | Human face identifying system and method |
| CN103310190A (en) * | 2012-05-16 | 2013-09-18 | 清华大学 | Facial image sample acquiring and optimizing method based on heterogeneous active vision network |
| CN103310190B (en) * | 2012-05-16 | 2016-04-13 | 清华大学 | Based on the facial image sample collection optimization method of isomery active vision network |
| CN103279740B (en) * | 2013-05-15 | 2016-06-29 | 吴玉平 | A kind of method and system utilizing dynamic data base to accelerate intelligent monitoring recognition of face |
| CN103279740A (en) * | 2013-05-15 | 2013-09-04 | 吴玉平 | Method and system for accelerating intelligent monitoring human face identification by utilizing dynamic database |
| CN104375892A (en) * | 2014-11-14 | 2015-02-25 | 广东欧珀移动通信有限公司 | Method and device capable of achieving face recognition through intelligent and quick start and mobile terminal |
| CN104375892B (en) * | 2014-11-14 | 2018-05-25 | 广东欧珀移动通信有限公司 | A kind of intelligence quickly starts the method, device and mobile terminal for realizing recognition of face |
| WO2016184276A1 (en) * | 2015-05-20 | 2016-11-24 | 腾讯科技（深圳）有限公司 | Evaluation method and evaluation device for facial key point positioning result |
| US10331940B2 (en) | 2015-05-20 | 2019-06-25 | Tencent Technology (Shenzhen) Company Limited | Evaluation method and evaluation device for facial key point positioning result |
| US10706263B2 (en) | 2015-05-20 | 2020-07-07 | Tencent Technology (Shenzhen) Company Limited | Evaluation method and evaluation device for facial key point positioning result |
| CN107292841A (en) * | 2017-06-16 | 2017-10-24 | 石福荣 | Medelling image processing techniques |
| CN108875474A (en) * | 2017-07-18 | 2018-11-23 | 北京旷视科技有限公司 | Assess the method, apparatus and computer storage medium of face recognition algorithms |
| CN108874657A (en) * | 2017-07-18 | 2018-11-23 | 北京旷视科技有限公司 | The method, apparatus and computer storage medium that recognition of face host is tested |
| CN107181766A (en) * | 2017-07-25 | 2017-09-19 | 湖南中迪科技有限公司 | The management-control method and device of log-on message |
| CN107241197A (en) * | 2017-07-25 | 2017-10-10 | 湖南中迪科技有限公司 | Password management-control method, device and password management and control device |
| CN107679448A (en) * | 2017-08-17 | 2018-02-09 | 平安科技（深圳）有限公司 | Eyeball action-analysing method, device and storage medium |
| US10534957B2 (en) | 2017-08-17 | 2020-01-14 | Ping An Technology (Shenzhen) Co., Ltd. | Eyeball movement analysis method and device, and storage medium |
| CN107566907B (en) * | 2017-09-20 | 2019-08-30 | Oppo广东移动通信有限公司 | Video clipping method, device, storage medium and terminal |
| CN107566907A (en) * | 2017-09-20 | 2018-01-09 | 广东欧珀移动通信有限公司 | video clipping method, device, storage medium and terminal |
| CN109656800B (en) * | 2017-10-10 | 2023-02-24 | 百度在线网络技术（北京）有限公司 | Method and device for testing image recognition application, terminal and storage medium |
| CN109656800A (en) * | 2017-10-10 | 2019-04-19 | 百度在线网络技术（北京）有限公司 | Test method, device, terminal and the storage medium of image recognition application |
| CN111526290A (en) * | 2017-11-08 | 2020-08-11 | Oppo广东移动通信有限公司 | Image processing method, device, terminal and storage medium |
| US11151360B2 (en) | 2017-11-28 | 2021-10-19 | Tencent Technology (Shenzhen) Company Ltd | Facial attribute recognition method, electronic device, and storage medium |
| WO2019105285A1 (en) * | 2017-11-28 | 2019-06-06 | 腾讯科技（深圳）有限公司 | Facial attribute recognition method, electronic device, and storage medium |
| CN110309337A (en) * | 2018-03-14 | 2019-10-08 | 广州弘度信息科技有限公司 | A kind of centrally stored method and device of characteristic value for plurality of target recognizer |
| CN110309337B (en) * | 2018-03-14 | 2021-05-07 | 广州弘度信息科技有限公司 | Characteristic value centralized storage method and device for multiple target recognition algorithms |
| US11941529B2 (en) | 2018-09-20 | 2024-03-26 | Beijing Bytedance Network Technology Co., Ltd. | Method and apparatus for processing mouth image |
| WO2020056902A1 (en) * | 2018-09-20 | 2020-03-26 | 北京字节跳动网络技术有限公司 | Method and apparatus for processing mouth image |
| CN109558812A (en) * | 2018-11-13 | 2019-04-02 | 广州铁路职业技术学院（广州铁路机械学校） | The extracting method and device of facial image, experience system and storage medium |
| CN109558812B (en) * | 2018-11-13 | 2021-07-23 | 广州铁路职业技术学院（广州铁路机械学校） | Face image extraction method and device, practical training system and storage medium |
| CN109684498A (en) * | 2018-12-21 | 2019-04-26 | 北京贝思科技术有限公司 | Operation method, general-purpose platform and the storage medium of image analysis algorithm model |
| CN110097007A (en) * | 2019-04-30 | 2019-08-06 | 福建威盾科技集团有限公司 | A kind of method and device for integrating a variety of face recognition engines |
| CN110287781A (en) * | 2019-05-17 | 2019-09-27 | 江苏大学 | Recognition of face and speech synthesis emerging system |
| 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 |
| CN110956129A (en) * | 2019-11-28 | 2020-04-03 | 重庆中星微人工智能芯片技术有限公司 | Method, apparatus, device and medium for generating face feature vector |
| CN111275023A (en) * | 2020-03-19 | 2020-06-12 | 中国人民解放军国防科技大学 | Push-up test system based on face recognition and human body posture estimation |
| CN111275023B (en) * | 2020-03-19 | 2023-04-18 | 中国人民解放军国防科技大学 | Push-up test system based on face recognition and human body posture estimation |
| WO2022001096A1 (en) * | 2020-06-30 | 2022-01-06 | 公安部第三研究所 | Facial test database management system for detection of facial recognition device, and method |
| CN111782835A (en) * | 2020-06-30 | 2020-10-16 | 公安部第三研究所 | Face test database management system and method for face recognition equipment detection |
| CN111782835B (en) * | 2020-06-30 | 2024-02-27 | 公安部第三研究所 | Face test database management system and method for face recognition equipment detection |
| CN112634520A (en) * | 2020-12-12 | 2021-04-09 | 上海应用技术大学 | Protection material distribution system based on face recognition technology |
| CN112733717A (en) * | 2021-01-11 | 2021-04-30 | 广州市金其利信息科技有限公司 | Method for optimizing face recognition based on face attributes |
| CN112733717B (en) * | 2021-01-11 | 2021-11-23 | 广州市金其利信息科技有限公司 | Method for optimizing face recognition based on face attributes |
| CN113177489A (en) * | 2021-05-07 | 2021-07-27 | 艾拉物联网络(深圳)有限公司 | High-precision portrait recognition method and system for security monitoring |
| CN113177489B (en) * | 2021-05-07 | 2021-12-07 | 艾拉物联网络(深圳)有限公司 | High-precision portrait recognition method and system for security monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101706872A (en) | Universal open type face identification system | |
| CN111325115B (en) | Cross-modal countervailing pedestrian re-identification method and system with triple constraint loss | |
| CN100481112C (en) | Human face recognition system and recognition method | |
| CN102804208B (en) | Individual model for visual search application automatic mining famous person | |
| CN106294344B (en) | Video retrieval method and device | |
| CN110781829A (en) | Light-weight deep learning intelligent business hall face recognition method | |
| CN102187336B (en) | Method for identifying an object in a video archive | |
| CN109325443A (en) | A kind of face character recognition methods based on the study of more example multi-tag depth migrations | |
| CN106203490A (en) | Based on attribute study and the image ONLINE RECOGNITION of interaction feedback, search method under a kind of Android platform | |
| CN106022241B (en) | A kind of face identification method based on wavelet transformation and rarefaction representation | |
| Parikh | Recognizing jumbled images: The role of local and global information in image classification | |
| CN1613090A (en) | Face meta-data creation | |
| CN103186538A (en) | Image classification method, image classification device, image retrieval method and image retrieval device | |
| CN110490238A (en) | A kind of image processing method, device and storage medium | |
| CN101334780A (en) | Figure image searching method, system and recording media for storing image metadata | |
| CN106407369A (en) | Photo management method and system based on deep learning face recognition | |
| CN107911643A (en) | Show the method and apparatus of scene special effect in a kind of video communication | |
| CN102339384B (en) | Face recognition method | |
| CN109670423A (en) | A kind of image identification system based on deep learning, method and medium | |
| CN108268886A (en) | For identifying the method and system of plug-in operation | |
| CN110688888B (en) | Pedestrian attribute identification method and system based on deep learning | |
| CN102222232A (en) | Multi-level rapid filtering and matching device and method for human faces | |
| CN114913923A (en) | Cell type identification method aiming at open sequencing data of single cell chromatin | |
| CN114639152A (en) | Multi-modal voice interaction method, device, equipment and medium based on face recognition | |
| CN110414792A (en) | Component centralized procurement management system and Related product based on BIM and big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: SHANGHAI HONGJIAN INTELLIGENT TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: SHANGHAI JIAOTONG UNIVERSITY Effective date: 20100609 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 200240 NO.800, DONGCHUAN ROAD, MINHANG DISTRICT, SHANGHAI CITY TO: 201203 216B, NO.518, BIBO ROAD, ZHANGJIANG HIGH SCIENCE PARK,PUDONG, SHANGHAI CITY |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20100609 Address after: 201203, Shanghai Zhangjiang hi tech park, Pudong, No. 518 blue wave road, 216B Applicant after: Shanghai Hongjian Intelligence Technology Co., Ltd. Address before: 200240 Dongchuan Road, Shanghai, No. 800, No. Applicant before: Shanghai Jiao Tong University |
|
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20100512 |