CN108229362B - Binocular face recognition living body detection method based on access control system - Google Patents
Binocular face recognition living body detection method based on access control system Download PDFInfo
- Publication number
- CN108229362B CN108229362B CN201711452118.8A CN201711452118A CN108229362B CN 108229362 B CN108229362 B CN 108229362B CN 201711452118 A CN201711452118 A CN 201711452118A CN 108229362 B CN108229362 B CN 108229362B
- Authority
- CN
- China
- Prior art keywords
- face
- living body
- video image
- control system
- door
- 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.)
- Active
Links
Images
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
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a binocular face recognition living body detection method based on an access control system. The method specifically comprises the following steps: (1) a binocular acquisition system is adopted to acquire video images; (2) carrying out face detection on the collected color video image; (3) if the human face is detected, analyzing the color video image and the infrared video image; (4) carrying out classification detection on the picture and the living body by utilizing a machine-learned SVM living body detection classifier; (5) matching and recognizing the collected human face and the human face bottom library, if the matching is successful, indicating that the human face recognition is successful, and controlling the door to be opened by the access control system; and if the matching is unsuccessful, the access control system does not open the door. The invention has the beneficial effects that: the cost is low, the algorithm speed is high, and the algorithm effect can be ensured; in addition, the detection accuracy rate of the living body detection can be improved to a great extent by matching with the analysis of the color image and the infrared image, and the user does not need to cooperate to act, so that the method is quicker and more convenient.
Description
Technical Field
The invention relates to the technical field related to biological pattern recognition, in particular to a binocular face recognition living body detection method based on an access control system.
Background
With the development of the biometric technology and the pattern recognition technology, the face recognition technology is mature, the face recognition system can well perform face detection and recognition, but for the access control system, a user can deceive the system by using a photo, so that research is needed to solve the defects existing in the prior art, and the crisis that the access control system is broken by using the photo is avoided.
The existing binocular face recognition living body detection mainly adopts three schemes: 1. the living body detection is carried out in coordination with the actions, and the user needs to coordinate with a series of specified actions such as shaking head, blinking, opening mouth and the like to judge whether the living body is a living body. 2. Whether a video acquired by the monocular camera is a living body is judged by using an image algorithm, and because the face and the picture of the living body acquired by the camera are two-dimensional images, the picture or the face is difficult to distinguish by using a simple image algorithm, and the detection rate is low. 3. The depth camera is used for 3D modeling to judge whether the living body is the living body, but the method not only needs to add the depth camera, but also has expensive cost, complex 3D modeling algorithm and low operation speed.
Disclosure of Invention
The invention provides the binocular face recognition living body detection method based on the access control system, which has high detection efficiency and high detection accuracy and is used for overcoming the defects in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a binocular face recognition living body detection method based on an access control system specifically comprises the following steps:
(1) a binocular acquisition system is adopted to acquire video images, and color video images and infrared video images are acquired respectively;
(2) carrying out face detection on the collected color video image, carrying out next analysis if the face is detected, and if the face is not detected, indicating that the color video image is a non-living body, terminating the step and not carrying out face identification;
(3) analyzing the color video image and the infrared video image, if the conditions of the color video image and the infrared video image are met at the same time, performing the next step, otherwise, judging that the black-white picture is not a living body, terminating the step and not performing face recognition;
(4) classifying and detecting the photo and the living body by using a machine-learned SVM living body detection classifier, if the living body is judged, carrying out next human face comparison, if the living body is judged, indicating that the living body is not a living body, and terminating the step;
(5) matching and recognizing the collected human face and the human face bottom library, if the matching is successful, the human face recognition is successful, the user is a legal user, and the door access system controls the door to be opened; if the matching is unsuccessful, the face recognition is failed, the user is an illegal user, and the door control system does not open the door.
The invention mainly utilizes an image algorithm to analyze the color video image and the infrared video image, and the acquisition system distinguishes whether the black-and-white picture is the black-and-white picture or not from the image characteristics of the video image acquired by the living human face because the image characteristics are obviously different. Although the image analysis module can eliminate the attack of black and white photos on the system, the attack of color photos on the system cannot be eliminated, so that the photos and living bodies are classified and detected by using the SVM classifier of machine learning. The binocular camera is adopted, so that the cost is low, the algorithm speed is high, and the algorithm effect can be guaranteed; in addition, the detection accuracy rate of the living body detection can be improved to a great extent by matching with the analysis of the color image and the infrared image, and the user does not need to cooperate to act, so that the method is quicker and more convenient.
Preferably, in step (1), the binocular shooting system includes a camera with a color camera and a camera with an infrared camera, and the two cameras shoot video images, wherein: the camera with the color camera collects color video images, the camera with the infrared camera collects infrared video images, and the two cameras are located on the same parallel line and collect images simultaneously. Wherein: the parallel camera is more favorable to the production of hardware equipment than other positions like the arc, and the convenient integrated binocular camera of hardware reduces manufacturing cost, and the video that the parallel camera was shot is favorable to the modeling of algorithm, and algorithm model complexity is low, promotes the arithmetic speed.
Preferably, in step (2), the face detection adopts a classic machine learning algorithm Adaboost face detection algorithm.
Preferably, in step (3), the conditions for satisfying the color video image are: the similarity of the RGB components of the color video image is greater than a threshold T1; the conditions for satisfying the infrared video image are as follows: the histogram contrast C of the infrared video image is greater than the threshold T2, and the calculation formula of C is as follows:
C＝∑[δ(i,j)]2p (i, j); wherein: t1 is an empirical value, T2 is an empirical value, δ (i, j) ═ i-j |, which is a gray scale difference between adjacent pixels, and P (i, j) is a pixel distribution probability of a gray scale difference between adjacent pixels. The principle in which the RGB components of a color video image have a similarity greater than a threshold T1 is: if the images are black and white photos, the color components of the images acquired by the color camera are relatively close and very similar, and the threshold value of T1 is generally 0.78 and can be adjusted according to the use scene. The infrared image generally refers to thermal imaging, if the object is not a living body, the temperature difference between the object (photo) in the scene and the background is lower than that of the living body, the dynamic range of the infrared image is large, the contrast is low, and according to the characteristic, the temperature difference between the object (photo) and the background in the scene is lower than that of the living body, the dynamic range of the infrared image is large, and the contrast is lowAn algorithm is designed to judge the living body and the picture, and T2 generally takes a value of 1.8.
Preferably, in step (4), the machine-learned SVM live body detection classifier is trained using two sets of samples of color photographs and live body faces.
Preferably, in the step (5), the specific steps are as follows: comparing the faces by using the color video images, calculating a score by similarity of the collected faces and all the faces in the face bottom library, if the highest score is more than 80 minutes, indicating that the face comparison is successful, wherein the matched face is the face with the highest score in the bottom library, the face identification is successful, the matched face is a legal user, and the door access system controls to open the door; otherwise, the face comparison fails, the user is an illegal user, and the door control system does not open the door. Wherein: the value of 80 is most suitable, because if the setting is too large, the recognition rate is reduced, and some legal users are judged as illegal users by mistake under the condition of low quality of the collected photos, such as illumination or side faces; if too low, this can result in some people with similar growth being misidentified as others.
The invention has the beneficial effects that: the binocular camera is adopted, so that the cost is low, the algorithm speed is high, and the algorithm effect can be ensured; in addition, the detection accuracy rate of the living body detection can be improved to a great extent by matching with the analysis of the color image and the infrared image, and the user does not need to cooperate to act, so that the method is quicker and more convenient.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is further described with reference to the following figures and detailed description.
In the embodiment shown in fig. 1, a binocular face recognition live body detection method based on an access control system specifically includes the following steps:
(1) a binocular acquisition system is adopted to acquire video images, and color video images and infrared video images are acquired respectively;
binocular collection system is including the camera that is equipped with colored camera and the camera that is equipped with infrared camera, and two cameras carry out video image and gather, wherein: the camera with the color camera collects color video images, the camera with the infrared camera collects infrared video images, and the two cameras are positioned on the same parallel line and collect images simultaneously; compared with other positions such as an arc, the parallel camera is more beneficial to the production of hardware equipment, the hardware is convenient to integrate the binocular camera, the production cost is reduced, the video shot by the parallel camera is beneficial to the modeling of an algorithm, the complexity of an algorithm model is low, and the operation speed is improved;
(2) carrying out face detection on the collected color video image, wherein the face detection adopts a classic machine learning algorithm Adaboost face detection algorithm, if a face is detected, the next step of analysis is carried out, if no face is detected, the image is a non-living body, the step is terminated, and face identification is not carried out;
(3) analyzing the color video image and the infrared video image, if the conditions of the color video image and the infrared video image are met at the same time, performing the next step, otherwise, judging that the black-white picture is not a living body, terminating the step and not performing face recognition;
(4) classifying and detecting the photo and the living body by using a machine-learned SVM living body detection classifier, if the living body is judged, carrying out next human face comparison, if the living body is judged, indicating that the living body is not a living body, and terminating the step;
the conditions for satisfying a color video image are: the similarity of the RGB components of the color video image is greater than a threshold T1; if the images are black and white photos, the color components of the images acquired by the color camera are relatively close and very similar, and the threshold value of T1 is generally 0.78 and can be adjusted according to the use scene;
the conditions for satisfying the infrared video image are as follows: the histogram contrast C of the infrared video image is greater than the threshold T2, and the calculation formula of C is as follows: c ═ Σ [ δ (i, j)]2P (i, j); the infrared image generally refers to thermal imaging, if the image is not a living body, the temperature difference between a target (picture) and a background in a scene is lower than that of the living body, the dynamic range of the infrared image is large, the contrast is low, the living body and the picture are judged according to an algorithm designed according to the characteristics, and the threshold value of T2 generally takes 1.8;
wherein: t1 is an empirical value, T2 is an empirical value, δ (i, j) ═ i-j |, which is a gray level difference between adjacent pixels, and P (i, j) is a pixel distribution probability of a gray level difference between adjacent pixels;
(5) matching and recognizing the collected human face and the human face bottom library, if the matching is successful, the human face recognition is successful, the user is a legal user, and the door access system controls the door to be opened; if the matching is unsuccessful, the face recognition is failed, the user is an illegal user, and the door control system does not open the door;
the method comprises the following specific steps: comparing the faces by using the color video images, calculating a score by similarity of the collected faces and all the faces in the face bottom library, if the highest score is more than 80 minutes, indicating that the face comparison is successful, wherein the matched face is the face with the highest score in the bottom library, the face identification is successful, the matched face is a legal user, and the door access system controls to open the door; otherwise, the face comparison fails, the user is an illegal user, and the door control system does not open the door. Wherein: the value of 80 is most suitable, because if the setting is too large, the recognition rate is reduced, and some legal users are judged as illegal users by mistake under the condition of low quality of the collected photos, such as illumination or side faces; if too low, this can result in some people with similar growth being misidentified as others.
The invention mainly utilizes an image algorithm to analyze the color video image and the infrared video image, and the acquisition system distinguishes whether the black-and-white picture is the black-and-white picture or not from the image characteristics of the video image acquired by the living human face because the image characteristics are obviously different. Although the image analysis module can eliminate the attack of black and white photos on the system, the attack of color photos on the system cannot be eliminated, so that the photos and living bodies are classified and detected by using the SVM classifier of machine learning. The binocular camera is adopted, so that the cost is low, the algorithm speed is high, and the algorithm effect can be guaranteed; in addition, the detection accuracy rate of the living body detection can be improved to a great extent by matching with the analysis of the color image and the infrared image, and the user does not need to cooperate to act, so that the method is quicker and more convenient.
Claims (5)
1. A binocular face recognition living body detection method based on an access control system is characterized by comprising the following steps:
(1) a binocular acquisition system is adopted to acquire video images, and color video images and infrared video images are acquired respectively;
(2) carrying out face detection on the collected color video image, carrying out next analysis if the face is detected, and if the face is not detected, indicating that the color video image is a non-living body, terminating the step and not carrying out face identification;
(3) analyzing the color video image and the infrared video image, if the conditions of the color video image and the infrared video image are met at the same time, performing the next step, otherwise, judging that the black-white picture is not a living body, terminating the step and not performing face recognition;
(4) classifying and detecting the photo and the living body by using a machine-learned SVM living body detection classifier, if the living body is judged, carrying out next human face comparison, if the living body is judged, indicating that the living body is not a living body, and terminating the step; the conditions for satisfying a color video image are: the similarity of the RGB components of the color video image is greater than a threshold T1; the conditions for satisfying the infrared video image are as follows: the histogram contrast C of the infrared video image is greater than the threshold T2, and the calculation formula of C is as follows: c ═ Σ [ δ (i, j)]2P (i, j); wherein: t1 is an empirical value, T2 is an empirical value, δ (i, j) ═ i-j |, which is a gray level difference between adjacent pixels, and P (i, j) is a pixel distribution probability of a gray level difference between adjacent pixels;
(5) matching and recognizing the collected human face and the human face bottom library, if the matching is successful, the human face recognition is successful, the user is a legal user, and the door access system controls the door to be opened; if the matching is unsuccessful, the face recognition is failed, the user is an illegal user, and the door control system does not open the door.
2. The binocular face recognition live body detection method based on the access control system as claimed in claim 1, wherein in the step (1), the binocular acquisition system comprises a camera with a color camera and a camera with an infrared camera, and the two cameras are used for video image acquisition, wherein: the camera with the color camera collects color video images, the camera with the infrared camera collects infrared video images, and the two cameras are located on the same parallel line and collect images simultaneously.
3. The binocular face recognition live body detection method based on the access control system as claimed in claim 1, wherein in the step (2), the face detection adopts a classic machine learning algorithm Adaboost face detection algorithm.
4. The binocular face recognition and live body detection method based on the access control system as claimed in claim 1, wherein in the step (4), the two groups of samples of the color photograph and the live body face are used for training a SVM live body detection classifier for machine learning.
5. The binocular face recognition live body detection method based on the access control system as claimed in claim 1, wherein in the step (5), the specific steps are as follows: comparing the faces by using the color video images, calculating a score by similarity of the collected faces and all the faces in the face bottom library, if the highest score is more than 80 minutes, indicating that the face comparison is successful, wherein the matched face is the face with the highest score in the bottom library, the face identification is successful, the matched face is a legal user, and the door access system controls to open the door; otherwise, the face comparison fails, the user is an illegal user, and the door control system does not open the door.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711452118.8A CN108229362B (en) | 2017-12-27 | 2017-12-27 | Binocular face recognition living body detection method based on access control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711452118.8A CN108229362B (en) | 2017-12-27 | 2017-12-27 | Binocular face recognition living body detection method based on access control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108229362A CN108229362A (en) | 2018-06-29 |
| CN108229362B true CN108229362B (en) | 2021-12-21 |
Family
ID=62649288
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711452118.8A Active CN108229362B (en) | 2017-12-27 | 2017-12-27 | Binocular face recognition living body detection method based on access control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108229362B (en) |
Families Citing this family (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117752A (en) * | 2018-07-24 | 2019-01-01 | 广州市国锐科技有限公司 | A kind of face recognition method based on gray scale and RGB |
| CN109147116A (en) * | 2018-07-25 | 2019-01-04 | 深圳市飞瑞斯科技有限公司 | The method that smart lock and control smart lock are opened |
| CN109145817A (en) * | 2018-08-21 | 2019-01-04 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of face In vivo detection recognition methods |
| EP3624032B1 (en) * | 2018-09-14 | 2023-08-16 | RDS Global Limited | Apparatus, method and computer program for linking a plurality of network input/output entities |
| CN109389719B (en) * | 2018-09-29 | 2021-01-26 | 厦门狄耐克智能科技股份有限公司 | Community door access control system and door opening method |
| CN111046703B (en) * | 2018-10-12 | 2023-04-18 | 杭州海康威视数字技术股份有限公司 | Face anti-counterfeiting detection method and device and multi-view camera |
| CN109636956A (en) * | 2018-10-26 | 2019-04-16 | 深圳云天励飞技术有限公司 | A kind of access control system control method, device and electronic equipment |
| CN109766849B (en) * | 2019-01-15 | 2023-06-20 | 深圳市凯广荣科技发展有限公司 | Living body detection method, detection device and self-service terminal equipment |
| CN110008878B (en) * | 2019-03-27 | 2021-07-30 | 熵基科技股份有限公司 | Anti-fake method for face detection and face recognition device with anti-fake function |
| CN110335379A (en) * | 2019-05-30 | 2019-10-15 | 深圳市威富视界有限公司 | Intelligent door lock control method based on recognition of face |
| CN110363087B (en) * | 2019-06-12 | 2022-02-25 | 苏宁云计算有限公司 | Long-baseline binocular face in-vivo detection method and system |
| CN110427887B (en) * | 2019-08-02 | 2023-03-10 | 腾讯科技（深圳）有限公司 | Member identity identification method and device based on intelligence |
| CN110503760B (en) * | 2019-08-27 | 2021-06-01 | 海信集团有限公司 | Access control method and access control system |
| CN110555930B (en) * | 2019-08-30 | 2021-03-26 | 北京市商汤科技开发有限公司 | Door lock control method and device, electronic equipment and storage medium |
| CN110555931A (en) * | 2019-08-31 | 2019-12-10 | 华南理工大学 | Face detection and gate inhibition system device based on deep learning recognition |
| CN111063079B (en) * | 2019-11-27 | 2022-04-15 | 深圳云天励飞技术有限公司 | Binocular living body face detection method and device based on access control system |
| CN110991301A (en) * | 2019-11-27 | 2020-04-10 | 成都超有范儿科技有限公司 | Face recognition method |
| CN111178249A (en) * | 2019-12-27 | 2020-05-19 | 杭州艾芯智能科技有限公司 | Face comparison method and device, computer equipment and storage medium |
| CN111444831B (en) * | 2020-03-25 | 2023-03-21 | 深圳中科信迅信息技术有限公司 | Method for recognizing human face through living body detection |
| TWI722872B (en) * | 2020-04-17 | 2021-03-21 | 技嘉科技股份有限公司 | Face recognition device and face recognition method |
| CN111738065A (en) * | 2020-05-11 | 2020-10-02 | 广东天波信息技术股份有限公司 | Face recognition access control method and system |
| CN112052729B (en) * | 2020-07-30 | 2024-04-16 | 广州市标准化研究院 | Intelligent dynamic high-definition video detection method and system based on face recognition |
| CN111914769B (en) * | 2020-08-06 | 2024-01-26 | 腾讯科技（深圳）有限公司 | User validity determination method, device, computer readable storage medium and equipment |
| CN113192358A (en) * | 2021-04-26 | 2021-07-30 | 贵州车秘科技有限公司 | Parking management system based on thermal imaging technology in intelligent parking field and use method thereof |
| CN113298993A (en) * | 2021-04-29 | 2021-08-24 | 杭州魔点科技有限公司 | Personnel access management method and system based on face recognition |
| CN113205058A (en) * | 2021-05-18 | 2021-08-03 | 中国科学院计算技术研究所厦门数据智能研究院 | Face recognition method for preventing non-living attack |
| CN114093004B (en) * | 2021-11-25 | 2023-05-02 | 成都智元汇信息技术股份有限公司 | Face fusion comparison method and device based on multiple cameras |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117695B (en) * | 2015-08-18 | 2017-11-24 | 北京旷视科技有限公司 | In vivo detection equipment and biopsy method |
| CN105930780A (en) * | 2016-04-14 | 2016-09-07 | 苏州优化智能科技有限公司 | Near infrared and micro expression based living body identity verification method |
| CN105912908A (en) * | 2016-04-14 | 2016-08-31 | 苏州优化智能科技有限公司 | Infrared-based real person living body identity verification method |
| CN106650669A (en) * | 2016-12-27 | 2017-05-10 | 重庆邮电大学 | Face recognition method for identifying counterfeit photo deception |
-
2017
- 2017-12-27 CN CN201711452118.8A patent/CN108229362B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108229362A (en) | 2018-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229362B (en) | Binocular face recognition living body detection method based on access control system | |
| CN107862299B (en) | Living body face detection method based on near-infrared and visible light binocular cameras | |
| CN108921041A (en) | A kind of biopsy method and device based on RGB and IR binocular camera | |
| Shao et al. | Deep convolutional dynamic texture learning with adaptive channel-discriminability for 3D mask face anti-spoofing | |
| CN108764058B (en) | Double-camera face in-vivo detection method based on thermal imaging effect | |
| US8027521B1 (en) | Method and system for robust human gender recognition using facial feature localization | |
| CN108446690B (en) | Human face in-vivo detection method based on multi-view dynamic features | |
| CN104361326A (en) | Method for distinguishing living human face | |
| KR20170006355A (en) | Method of motion vector and feature vector based fake face detection and apparatus for the same | |
| CN111523344B (en) | Human body living body detection system and method | |
| EP3905104B1 (en) | Living body detection method and device | |
| CN105975938A (en) | Smart community manager service system with dynamic face identification function | |
| CN110414314A (en) | A kind of camera structure carrying out Face tracking and recognition and system | |
| CN105335691A (en) | Smiling face identification and encouragement system | |
| CN104408780A (en) | Face recognition attendance system | |
| CN111582197A (en) | Living body based on near infrared and 3D camera shooting technology and face recognition system | |
| CN108268825A (en) | Three-dimensional face tracking and expression recognition system based on mobile holder | |
| CN112818722A (en) | Modular dynamically configurable living body face recognition system | |
| CN106203497A (en) | A kind of finger vena area-of-interest method for screening images based on image quality evaluation | |
| WO2013075295A1 (en) | Clothing identification method and system for low-resolution video | |
| CN111967319A (en) | Infrared and visible light based in-vivo detection method, device, equipment and storage medium | |
| CN108446642A (en) | A kind of Distributive System of Face Recognition | |
| CN107862298B (en) | Winking living body detection method based on infrared camera device | |
| CN107247934A (en) | A kind of round-the-clock yawn detection method and system based on swift nature point location | |
| CN102831379B (en) | facial image recognition method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |