CN110222623A - Micro- expression analysis method and system - Google Patents
Micro- expression analysis method and system Download PDFInfo
- Publication number
- CN110222623A CN110222623A CN201910471070.8A CN201910471070A CN110222623A CN 110222623 A CN110222623 A CN 110222623A CN 201910471070 A CN201910471070 A CN 201910471070A CN 110222623 A CN110222623 A CN 110222623A
- Authority
- CN
- China
- Prior art keywords
- face
- micro
- expression
- image data
- characteristic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000010195 expression analysis Methods 0.000 title claims abstract description 16
- 230000014509 gene expression Effects 0.000 claims abstract description 66
- 230000036651 mood Effects 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 241001269238 Data Species 0.000 claims abstract description 15
- 238000013135 deep learning Methods 0.000 claims abstract description 14
- 210000000887 face Anatomy 0.000 claims description 7
- 210000004709 eyebrow Anatomy 0.000 claims description 4
- 210000001097 facial muscle Anatomy 0.000 claims description 4
- 230000004297 night vision Effects 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims 1
- 239000000284 extract Substances 0.000 description 12
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000011521 glass Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of micro- expression analysis method and systems.Micro- expression analysis method includes: the image data of the various angles under the different micro- expressions of a large amount of faces of acquisition；Network is extracted to the face characteristic of a large amount of face image datas building deep learning；Network is extracted to face characteristic by fine tuning and carries out precision improvement, obtains feature weight Parameter File library；To the image data of the micro- expression of freshly harvested face, network is extracted by face characteristic and carries out feature extraction, obtains characteristic parameter file；Characteristic parameter file and feature weight Parameter File library are compared, determine the mood classification of the micro- expression of face in freshly harvested image.The micro- expression of face is identified by various dimensions, can effectively improve the accuracy of the micro- Expression Recognition result of face.
Description
Technical field
The present invention relates to micro- Expression Recognition technical fields, more particularly to a kind of micro- expression analysis method and system.
Background technique
Micro- Expression Recognition technology is the intelligent identification technology in conjunction with image processing techniques and mode identification technology, is led in security protection
Domain is widely applied, for example, the hearing of a suspect, monitors the personnel of the suspicious mood in public place, the hair of crime prevention
It is raw；Applied to nurse, the real-time concern of infant's state, the care of depression child growth；Applied to business, by client
The corresponding interested content etc. of the changing push of mood.
However, traditional micro- expression recognition method only identifies the micro- expression of face from single dimension, testing result is deposited
The not high problem of accuracy.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of face micro- Expression Recognition result accuracys of capable of effectively improving
Micro- expression analysis method and system.
To achieve the purpose of the present invention, the present invention adopts the following technical scheme:
A kind of micro- expression analysis method, includes the following steps:
Acquire the image data of the various angles under the different micro- expressions of a large amount of faces；
Network is extracted to the face characteristic of a large amount of face image datas building deep learning；
Network is extracted to the face characteristic by fine tuning and carries out precision improvement, obtains feature weight Parameter File library；
To the image data of the micro- expression of freshly harvested face, network is extracted by the face characteristic and carries out feature extraction,
Obtain characteristic parameter file；
The characteristic parameter file and feature weight Parameter File library are compared, determined in freshly harvested image
The micro- expression of face mood classification.
Above-mentioned micro- expression analysis method, the picture number including acquiring the various angles under the different micro- expressions of a large amount of faces
According to；Network is extracted to the face characteristic of a large amount of face image datas building deep learning；Net is extracted to face characteristic by fine tuning
Network carries out precision improvement, obtains feature weight Parameter File library；To the image data of the micro- expression of freshly harvested face, pass through face
Feature extraction network carries out feature extraction, obtains characteristic parameter file；By characteristic parameter file and feature weight Parameter File library
It compares, determines the mood classification of the micro- expression of face in freshly harvested image.The micro- expression of face is carried out by various dimensions
Identification, can effectively improve the accuracy of the micro- Expression Recognition result of face.
The different micro- expressions of the face include eyebrow turning, nose, the corners of the mouth and facial muscles in one of the embodiments,
Variation.
The face characteristic to a large amount of face image datas building deep learning extracts net in one of the embodiments,
Before the step of network, comprising:
Acquired image data are pre-processed, by the destination image data and background image data in image data
It is separated.
To achieve the purpose of the present invention, the present invention also adopts the following technical scheme that
A kind of micro- expression studies and judges system, comprising:
The micro- expression acquisition module of face acquires the image data of the various angles under the different micro- expressions of a large amount of faces；
Module is constructed, network is extracted to the face characteristic of a large amount of face image datas building deep learning；
Module is finely tuned, network is extracted to the face characteristic by fine tuning and carries out precision improvement, obtains feature weight parameter
Library；
Characteristic extracting module extracts network by the face characteristic to the image data of the micro- expression of freshly harvested face
Feature extraction is carried out, characteristic parameter file is obtained；
Contrast module compares the characteristic parameter file and feature weight Parameter File library, and determination is newly adopted
The mood classification of face mood in the image of collection.
Micro- expression studies and judges system in one of the embodiments, further include:
Target image extraction module pre-processes acquired image data, by the target image in image data
Data are separated with background image data.
The micro- expression acquisition module of the face uses face snap machine, face snap equipment in one of the embodiments,
Standby wide dynamic, the function of anti-backlight and infrared night vision.
Detailed description of the invention
Fig. 1 is the flow diagram of micro- expression analysis method in an embodiment；
Fig. 2 is the flow diagram of micro- expression analysis method in another embodiment；
Fig. 3 is the structural schematic diagram that micro- expression studies and judges system in an embodiment；
Fig. 4 is the structural schematic diagram that micro- expression studies and judges system in another embodiment.
Specific embodiment
To facilitate the understanding of the present invention, a more comprehensive description of the invention is given in the following sections with reference to the relevant attached drawings.In attached drawing
Give preferred embodiment of the invention.But the invention can be realized in many different forms, however it is not limited to this paper institute
The embodiment of description.On the contrary, purpose of providing these embodiments is make it is more thorough and comprehensive to the disclosure.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.
Referring to Fig. 1, present embodiments provide a kind of micro- expression analysis method, including step S10, step S20, step S30,
Step S40 and step S50, details are as follows:
In step slo, the image data of the various angles under the different micro- expressions of a large amount of faces is acquired.
In step S20, network is extracted to the face characteristic of a large amount of face image datas building deep learning.
In step s 30, network is extracted to face characteristic by fine tuning and carries out precision improvement, obtain feature weight parameter text
Part library.
In step s 40, to the image data of the micro- expression of freshly harvested face, network is extracted by face characteristic and carries out spy
Sign is extracted, and characteristic parameter file is obtained.
In step s 50, characteristic parameter file and feature weight Parameter File library are compared, determines freshly harvested figure
The mood classification of the micro- expression of face as in.
In the present embodiment, step S10, the image data of a large amount of different angles for collecting the different micro- expressions of face, in people
Extract some key points in face image data, for example, eyebrow turning, nose, the corners of the mouth, facial muscles different angle variation, row
Remove the interference of similar glasses, cap；Step S20 extracts the face characteristic of a large amount of face image datas building deep learning
Network；Step S30 extracts network to face characteristic by fine tuning and carries out precision improvement, finally obtains the higher feature of accuracy
Weight parameter library；In step S40, to the image data of the micro- expression of freshly harvested face, network is extracted by face characteristic
Feature extraction is carried out, characteristic parameter file is obtained；In step s 50, by characteristic parameter file and feature weight Parameter File library
It compares, determines the mood classification of the micro- expression of face in freshly harvested image.
Above-mentioned micro- expression analysis method, the picture number including acquiring the various angles under the different micro- expressions of a large amount of faces
According to；Network is extracted to the face characteristic of a large amount of face image datas building deep learning；Net is extracted to face characteristic by fine tuning
Network carries out precision improvement, obtains feature weight Parameter File library；To the image data of the micro- expression of freshly harvested face, pass through face
Feature extraction network carries out feature extraction, obtains characteristic parameter file；By characteristic parameter file and feature weight Parameter File library
It compares, determines the mood classification of the micro- expression of face in freshly harvested image.The micro- expression of face is carried out by various dimensions
Identification, can effectively improve the accuracy of the micro- Expression Recognition result of face.
In one embodiment, referring to fig. 2, net is extracted to the face characteristic of a large amount of face image datas building deep learning
Before the step of network, micro- expression analysis method further includes step S60.
In step S60, acquired image data are pre-processed, by image data destination image data with
Background image data is separated.
In the present embodiment, acquired image data are pre-processed, by the destination image data in image data
It is separated with background image data, can more accurately obtain face characteristic information.
Referring to Fig. 3, the present embodiment additionally provides a kind of micro- expression and studies and judges system, comprising:
The micro- expression acquisition module 100 of face acquires the image data of the various angles of the micro- expression of face.
Network struction module 200 extracts network to the face characteristic of a large amount of face image datas building deep learning；
Module 300 is finely tuned, network is extracted to face characteristic by fine tuning and carries out precision improvement, obtains feature weight parameter text
Part library.
Characteristic extracting module 400, to the image data of the micro- expression of freshly harvested face, by face characteristic extract network into
Row feature extraction, obtains characteristic parameter file.
Characteristic parameter file and feature weight Parameter File library are compared, determine freshly harvested figure by contrast module 500
The mood classification of face mood as in.
In the present embodiment, the micro- expression acquisition module 100 of face, a large amount of different angles for collecting the different micro- expressions of face
Image data extracts some key points, such as the difference at eyebrow turning, nose, the corners of the mouth, facial muscles in face image data
The variation of angle excludes the interference of similar glasses, cap；Network struction module 200 constructs a large amount of face image datas deep
The face characteristic of degree study extracts network；Module 300 is finely tuned, network is extracted to face characteristic by fine tuning and carries out precision improvement,
Finally obtain accuracy higher feature weight Parameter File library；Characteristic extracting module 400, to the micro- expression of freshly harvested face
Image data extracts network by face characteristic and carries out feature extraction, obtains characteristic parameter file；Contrast module 500, by feature
Parameter File is compared with feature weight Parameter File library, determines the mood class of the micro- expression of face in freshly harvested image
Not.
Above-mentioned micro- expression studies and judges system, comprising: the micro- expression acquisition module 100 of face acquires the various angles of the micro- expression of face
The image data of degree；Network struction module 200 extracts net to the face characteristic of a large amount of face image datas building deep learning
Network；Module 300 is finely tuned, network is extracted to face characteristic by fine tuning and carries out precision improvement, obtains feature weight Parameter File library；
Characteristic extracting module 400 extracts network by the face characteristic and carries out spy to the image data of the micro- expression of freshly harvested face
Sign is extracted, and characteristic parameter file is obtained；Contrast module 500 carries out characteristic parameter file and feature weight Parameter File library pair
Than determining the mood classification of the face mood in freshly harvested image.The micro- expression of face is identified by various dimensions, it can be with
Effectively improve the accuracy of the micro- Expression Recognition result of face.
In one embodiment, referring to fig. 4, micro- expression studies and judges system further include:
Target image extraction module 600 pre-processes acquired image data, by the target figure in image data
As data are separated with background image data.
In the present embodiment, target image extraction module 600 is by the destination image data and background image in image data
Data are separated, and face characteristic information can be more accurately obtained.
In one embodiment, the micro- expression acquisition module 100 of face uses face snap machine, and face snap equipment is standby wide dynamic
The function of state, anti-backlight and infrared night vision.
In the present embodiment, using exclusive face snap machine, wide dynamic, anti-backlight, infrared night vision helps quickly to cut
Take out the face picture of good quality, it is ensured that correct mood is obtained by clearly face characteristic and analyzes result.It can solve
Traditional technology is because environmental disturbances lead to the problem of mood analysis inaccuracy.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (6)
1. a kind of micro- expression analysis method, which comprises the steps of:
Acquire the image data of the various angles under the different micro- expressions of a large amount of faces；
Network is extracted to the face characteristic of a large amount of face image datas building deep learning；
Network is extracted to the face characteristic by fine tuning and carries out precision improvement, obtains feature weight Parameter File library；
To the image data of the micro- expression of freshly harvested face, network is extracted by the face characteristic and carries out feature extraction, is obtained
Characteristic parameter file；
The characteristic parameter file and feature weight Parameter File library are compared, determined in freshly harvested image data
The micro- expression of face mood classification.
2. micro- expression analysis method according to claim 1, which is characterized in that the different micro- expressions of the face include eyebrow
The variation at turning, nose, the corners of the mouth and facial muscles.
3. micro- expression analysis method according to claim 1, which is characterized in that described to be constructed to a large amount of face image datas
The face characteristic of deep learning extracted before the step of network, comprising:
Acquired image data are pre-processed, by the destination image data and background image data progress in image data
Separation.
4. a kind of micro- expression studies and judges system characterized by comprising
The micro- expression acquisition module of face acquires the image data of the various angles under the different micro- expressions of a large amount of faces；
Module is constructed, network is extracted to the face characteristic of a large amount of face image datas building deep learning；
Module is finely tuned, network is extracted to the face characteristic by fine tuning and carries out precision improvement, obtains feature weight Parameter File
Library；
Characteristic extracting module is extracted network by the face characteristic and is carried out to the image data of the micro- expression of freshly harvested face
Feature extraction obtains characteristic parameter file；
The characteristic parameter file and feature weight Parameter File library are compared, are determined freshly harvested by contrast module
The mood classification of face mood in image.
5. micro- expression according to claim 4 studies and judges system, which is characterized in that micro- expression studies and judges system further include:
Target image extraction module pre-processes acquired image data, by the destination image data in image data
It is separated with background image data.
6. micro- expression according to claim 4 studies and judges system, which is characterized in that the micro- expression acquisition module of face uses
Face snap machine, the standby wide dynamic of the face snap equipment, the function of anti-backlight and infrared night vision.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910471070.8A CN110222623A (en) | 2019-05-31 | 2019-05-31 | Micro- expression analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910471070.8A CN110222623A (en) | 2019-05-31 | 2019-05-31 | Micro- expression analysis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110222623A true CN110222623A (en) | 2019-09-10 |
Family
ID=67819177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910471070.8A Pending CN110222623A (en) | 2019-05-31 | 2019-05-31 | Micro- expression analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110222623A (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537336A (en) * | 2014-12-17 | 2015-04-22 | 厦门立林科技有限公司 | Face identification method and system with self-learning function |
| CN104850825A (en) * | 2015-04-18 | 2015-08-19 | 中国计量学院 | Facial image face score calculating method based on convolutional neural network |
| CN106096551A (en) * | 2016-06-14 | 2016-11-09 | 湖南拓视觉信息技术有限公司 | The method and apparatus of face part Identification |
| CN106503654A (en) * | 2016-10-24 | 2017-03-15 | 中国地质大学（武汉） | A kind of face emotion identification method based on the sparse autoencoder network of depth |
| CN106599800A (en) * | 2016-11-25 | 2017-04-26 | 哈尔滨工程大学 | Face micro-expression recognition method based on deep learning |
| CN106778584A (en) * | 2016-12-08 | 2017-05-31 | 南京邮电大学 | A kind of face age estimation method based on further feature Yu shallow-layer Fusion Features |
| CN107742116A (en) * | 2017-11-13 | 2018-02-27 | 湖南超能机器人技术有限公司 | A kind of infant emotion change detection and knowledge method for distinguishing |
| CN107798318A (en) * | 2017-12-05 | 2018-03-13 | 四川文理学院 | The method and its device of a kind of happy micro- expression of robot identification face |
| CN107832753A (en) * | 2017-12-21 | 2018-03-23 | 中通服公众信息产业股份有限公司 | A kind of face feature extraction method based on four value weights and multiple classification |
| CN108038455A (en) * | 2017-12-19 | 2018-05-15 | 中国科学院自动化研究所 | Bionic machine peacock image-recognizing method based on deep learning |
| CN108108723A (en) * | 2018-01-19 | 2018-06-01 | 深圳市恩钛控股有限公司 | A kind of face feature extraction method based on deep learning |
| CN108764169A (en) * | 2018-05-31 | 2018-11-06 | 厦门大学 | A kind of driver's Emotion identification based on machine learning and display device and method |
| CN109284713A (en) * | 2018-09-21 | 2019-01-29 | 上海健坤教育科技有限公司 | A kind of Emotion identification analysis system based on camera acquisition expression data |
| CN109460728A (en) * | 2018-10-31 | 2019-03-12 | 深圳市安视宝科技有限公司 | A kind of big data safeguard management platform based on Emotion identification |
| CN109766917A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Interview video data handling procedure, device, computer equipment and storage medium |
| CN109766766A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Employee work condition monitoring method, device, computer equipment and storage medium |
| CN109815826A (en) * | 2018-12-28 | 2019-05-28 | 新大陆数字技术股份有限公司 | The generation method and device of face character model |
| CN109815801A (en) * | 2018-12-18 | 2019-05-28 | 北京英索科技发展有限公司 | Face identification method and device based on deep learning |
-
2019
- 2019-05-31 CN CN201910471070.8A patent/CN110222623A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537336A (en) * | 2014-12-17 | 2015-04-22 | 厦门立林科技有限公司 | Face identification method and system with self-learning function |
| CN104850825A (en) * | 2015-04-18 | 2015-08-19 | 中国计量学院 | Facial image face score calculating method based on convolutional neural network |
| CN106096551A (en) * | 2016-06-14 | 2016-11-09 | 湖南拓视觉信息技术有限公司 | The method and apparatus of face part Identification |
| CN106503654A (en) * | 2016-10-24 | 2017-03-15 | 中国地质大学（武汉） | A kind of face emotion identification method based on the sparse autoencoder network of depth |
| CN106599800A (en) * | 2016-11-25 | 2017-04-26 | 哈尔滨工程大学 | Face micro-expression recognition method based on deep learning |
| CN106778584A (en) * | 2016-12-08 | 2017-05-31 | 南京邮电大学 | A kind of face age estimation method based on further feature Yu shallow-layer Fusion Features |
| CN107742116A (en) * | 2017-11-13 | 2018-02-27 | 湖南超能机器人技术有限公司 | A kind of infant emotion change detection and knowledge method for distinguishing |
| CN107798318A (en) * | 2017-12-05 | 2018-03-13 | 四川文理学院 | The method and its device of a kind of happy micro- expression of robot identification face |
| CN108038455A (en) * | 2017-12-19 | 2018-05-15 | 中国科学院自动化研究所 | Bionic machine peacock image-recognizing method based on deep learning |
| CN107832753A (en) * | 2017-12-21 | 2018-03-23 | 中通服公众信息产业股份有限公司 | A kind of face feature extraction method based on four value weights and multiple classification |
| CN108108723A (en) * | 2018-01-19 | 2018-06-01 | 深圳市恩钛控股有限公司 | A kind of face feature extraction method based on deep learning |
| CN108764169A (en) * | 2018-05-31 | 2018-11-06 | 厦门大学 | A kind of driver's Emotion identification based on machine learning and display device and method |
| CN109284713A (en) * | 2018-09-21 | 2019-01-29 | 上海健坤教育科技有限公司 | A kind of Emotion identification analysis system based on camera acquisition expression data |
| CN109460728A (en) * | 2018-10-31 | 2019-03-12 | 深圳市安视宝科技有限公司 | A kind of big data safeguard management platform based on Emotion identification |
| CN109766917A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Interview video data handling procedure, device, computer equipment and storage medium |
| CN109766766A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Employee work condition monitoring method, device, computer equipment and storage medium |
| CN109815801A (en) * | 2018-12-18 | 2019-05-28 | 北京英索科技发展有限公司 | Face identification method and device based on deep learning |
| CN109815826A (en) * | 2018-12-28 | 2019-05-28 | 新大陆数字技术股份有限公司 | The generation method and device of face character model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106650693B (en) | Multi-feature fusion recognition algorithm for face comparison | |
| US11263435B2 (en) | Method for recognizing face from monitoring video data | |
| CN105138954B (en) | A kind of image automatic screening inquiry identifying system | |
| Sun et al. | Improving iris recognition accuracy via cascaded classifiers | |
| CN109497990B (en) | Electrocardiosignal identity recognition method and system based on canonical correlation analysis | |
| US9064145B2 (en) | Identity recognition based on multiple feature fusion for an eye image | |
| CN109376725B (en) | Identity verification method and device based on iris recognition | |
| CN104143079A (en) | Method and system for face attribute recognition | |
| CN108009482A (en) | One kind improves recognition of face efficiency method | |
| CN104036247A (en) | Facial feature based face racial classification method | |
| CN104866829A (en) | Cross-age face verify method based on characteristic learning | |
| CN106203458A (en) | Crowd's video analysis method and system | |
| CN102902967A (en) | Method for positioning iris and pupil based on eye structure classification | |
| CN103793690A (en) | Human body biotic living body detection method based on subcutaneous bloodstream detection and application | |
| CN104008395A (en) | Intelligent bad video detection method based on face retrieval | |
| CN107947874B (en) | Indoor map semantic identification method based on WiFi channel state information | |
| CN107798276A (en) | A kind of facial aging method and device of facial image | |
| Chachere et al. | Real Time Face Mask Detection by using CNN | |
| CN104036291A (en) | Race classification based multi-feature gender judgment method | |
| CN104484651B (en) | Portrait dynamic contrast method and system | |
| CN104679967A (en) | Method for judging reliability of psychological test | |
| CN110889335A (en) | Human skeleton double-person interaction behavior recognition method based on multi-channel space-time fusion network | |
| Shashikala et al. | Attendance monitoring system using face recognition | |
| CN110222623A (en) | Micro- expression analysis method and system | |
| CN112329698A (en) | Face recognition method and system based on intelligent blackboard |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190910 |
|
| RJ01 | Rejection of invention patent application after publication |