CN110705454A - Face recognition method with living body detection function - Google Patents
Face recognition method with living body detection function Download PDFInfo
- Publication number
- CN110705454A CN110705454A CN201910930008.0A CN201910930008A CN110705454A CN 110705454 A CN110705454 A CN 110705454A CN 201910930008 A CN201910930008 A CN 201910930008A CN 110705454 A CN110705454 A CN 110705454A
- Authority
- CN
- China
- Prior art keywords
- face
- living body
- face recognition
- eye region
- detection function
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 23
- 239000013598 vector Substances 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 230000001815 facial effect Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 230000001629 suppression Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 8
- 230000007246 mechanism Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 6
- 230000004397 blinking Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000000193 eyeblink Effects 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Ophthalmology & Optometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention relates to a face recognition method with a living body detection function, which comprises the following steps: carrying out face detection on the acquired image by using image acquisition equipment, carrying out blink detection in a face area when a face is detected, and judging whether the detected face is a living body; and when the detected face is a living body, identifying the face by using the face identification model. The invention has simple calculation and easy realization, and improves the reliability and the safety of face recognition by adding a layer of protection mechanism.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a face recognition method with a living body detection function.
Background
Identity authentication is always an important link in all aspects of human life, and particularly in the modern society developing at a high speed, "quick, convenient and safe" becomes a pronoun of the contemporary society. With the rapid development of computer vision technology and artificial intelligence, identity authentication technology changes in daily commuting card punching systems, access control systems and the like. The accuracy of the identity authentication method from fingerprint identification, iris identification to face identification is higher and higher, and the face identification is most suitable for the recognition of the public due to the aspects of manufacturing cost and stability. But face identification has remote identification, has avoided the contact identification of similar fingerprint identification, and only need the camera gather data people's image can, can not be like iris identification the data set is difficult to gather to the cost is higher. By combining the reasons, the face recognition technology is widely recognized and applied, and the face recognition technology is widely applied to the aspects of mobile payment authentication, access control system authentication, bank account authentication and the like.
In recent years, with the continuous development of research in related subject fields such as image processing, computer vision, machine learning and the like, the face recognition technology is greatly improved in both academic research and engineering application, but the hidden danger exists along with the progress, because the face recognition is to recognize images, people who cannot recognize can pass authentication by holding pictures capable of recognizing people, and the hidden safety danger needs to be solved urgently.
Recently, blink recognition technology in vivo detection is mature and applied in various fields, and academic research and engineering application related to the technology are also endless. The living body detection technology is generated for identifying the deception of illegal users to the identity authentication system based on the face images. According to research and development, the conventional blink detection method is generally used for detecting the ratio change of the white part of eyes to eyes before and after blinking, and the method is complex in calculation and low in accuracy.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a face recognition method with a living body detection function, which is simple in calculation and easy to implement.
The technical scheme adopted by the invention for solving the technical problems is as follows: the face recognition method with the living body detection function comprises the following steps:
(1) carrying out face detection on the acquired image by using image acquisition equipment, carrying out blink detection in a face area when a face is detected, and judging whether the detected face is a living body;
(2) and when the detected face is a living body, identifying the face by using the face identification model.
When blink detection is performed in the step (1), firstly, an eye area of a human face is obtained, and 6 face feature points are arranged around an eyeglass area in a clockwise mode by taking the left corner of the eye area as a starting point; and calculating the length-width ratio of the eyes based on the 6 facial feature points, and judging whether the eyes blink according to the change condition of the length-width ratio of the eyes.
The eye length-width ratio is calculated in the mode ofWherein p is1Is the position of the feature point of the left corner face of the eye region, p2Is the position of the top left feature point of the eye region, p3Is the position of the feature point of the upper right of the eye region, p4Is the position of the feature point of the right-angle face of the eye region, p5Is the position of the lower right feature point of the eye region, p6The position of the lower left hand feature point of the eye region.
The face recognition model in the step (2) adopts MTCNN to detect and cut the face; the MTCNN is a cascade structure of three parts, wherein the first part is used for generating a candidate frame possibly having a face, the second part is used for taking the result of the first part as input, removing part of the candidate frame according to a non-maximum suppression method, and the third part is used for taking the result of the second part as input, further screening the candidate frame to obtain an accurate candidate frame and outputting face key points.
And (3) when the face recognition model in the step (2) is trained, sending the cut image with the face frame and the face key point into a pre-trained deep Facenet face recognition neural network, and training the face recognition model by adopting the pre-trained model.
When the human face is identified in the step (2), the human face is matched in an Annoy index mode, in the human face matching, the obtained human face feature vectors form a plurality of binary tree structures in an Annoy mode, when the human face is required to be identified for the new collected feature vectors, the binary trees are only required to be traversed respectively to obtain the feature vectors nearest to the target, and threshold control judgment is set, so that comparison and identity judgment are carried out.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: the invention carries out living body detection before face recognition, carries out face recognition only under the condition that a detection object is a living body, and improves the reliability and safety of face recognition by adding a layer of protection mechanism. In addition, when the living body detection is carried out, the method adopts the key points of the human eyes to judge the blink, the blink detection method avoids using an image processing technology, and the blink detection method can be realized only by calculating the length-width ratio of the key points of the human eyes.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a diagram of human eye feature point selection in the present invention;
fig. 3 is a schematic diagram of blink determination using EAR calculation formula in the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
The embodiment of the invention relates to a face recognition method with a living body detection function, which comprises the following steps as shown in figure 1: carrying out face detection on the acquired image by using image acquisition equipment, carrying out blink detection in a face area when a face is detected, and judging whether the detected face is a living body; and when the detected face is a living body, identifying the face by using the face identification model. The method comprises the following specific steps:
step 1: first, a face recognition model is trained. The method specifically comprises the following steps: preparing a data set, if an available face recognition model needs to be trained, firstly preparing a data set used for training the model, and performing a series of preprocessing including multi-scale change, rotation, brightness and darkness on a face photo to achieve the effect of data enhancement, improve the generalization capability of model training and prepare for a face detection part.
Step 2: face cropping, namely performing face detection on a large amount of face data sets by using an MTCNN (multiple-transmission-network) which is a cascade structure of three parts, wherein the first part is a candidate frame for generating a possible face, the number of the first layer of frames is very large, and the accuracy is not very high in the layer, so that a second layer of cascade is accessed, the second part is a candidate frame which takes the result of the first part as input, and redundant accuracy is not very high in the second layer of frames is removed according to methods such as non-maximum value inhibition and the like, so that the number of frames can be greatly reduced in the layer; and the last part is to take the result of the second part as input, further screen the candidate frame to obtain a more accurate candidate frame and output the key points of the human face.
And step 3: and model training, namely sending the cut image with the face frame and the face key point into a pre-trained deep Facenet face recognition neural network, and migrating a relatively mature pre-trained model.
And 4, step 4: live body detection, at first the camera of calling personal computer, use the cv2.videoCapture function in the opencv can call leading camera, in addition opencv is from taking the face detection model, direct call can carry out face detection, when detecting the face, can carry out blink detection in the face region, the benefit of detecting the face at first is, provides a guarantee before blink detection, double-fixing makes the effect more accurate.
And 5: and (4) blink detection, as shown in fig. 2, selecting six feature points of the eye images A to E. The distance between A, B remained substantially constant while the distance between C, D and E, F decreased rapidly to a small value when blinking of the human eye occurred, and the distance between A, E plus E, B was substantially equal to A, B. Based on this, the present embodiment can detect whether a blinking motion occurs or not based on the distance variation values between the six feature points.
For blink detection, the present embodiment only cares about the two eye regions of the human face. Each eye area is represented as 6 coordinates, i.e. starting from the left corner of the eye area, 6 facial feature points are arranged around the spectacle area in a clockwise manner based on the 6 facial feature points passingCalculating the aspect ratio of the eye, wherein p1Is the position of the feature point of the left corner face of the eye region, p2Is the position of the top left feature point of the eye region, p3Is the position of the feature point of the upper right of the eye region, p4Is the position of the feature point of the right-angle face of the eye region, p5Is the position of the lower right feature point of the eye region, p6The position of the lower left hand feature point of the eye region. As shown in fig. 3, the numerator of the EAR calculation formula is to calculate the distance between vertical eye landmarks and the denominator is to calculate the distance between horizontal eye landmarks, since there is only one set of horizontal points, but two sets of vertical points, the denominator is weighted. The EAR calculation remains approximately constant when the eye is open, but changes rapidly to zero when the eye blinks. Therefore, by using the EAR calculation formula, the image processing technology can be avoided, and only the length-width ratio of the eye feature key points needs to be calculated to judge whether a person blinks or not.
When the judgment is carried out, the distance between the two groups of vertical eye marks is firstly calculated according to an EAR calculation formula, and then the distance between the horizontal eye marks is calculated. Finally, the numerator and denominator are combined to arrive at the final eye aspect ratio. A threshold value is then set for the eye aspect ratio as is the case, and the eye aspect ratio in the case of a normal blink begins to fall below the set threshold value and then exceeds the set threshold value, then a "blink" will be recorded.
Step 6: if the living body detects blinking actions, namely the living body is acquired by default, then the trained face recognition model is called to perform face recognition. If no blinking motion is detected, namely the living body is not detected, the protection mechanism does not pass the subsequent face recognition operation, and the default recognition does not pass.
And 7: and when the living body detection and identification are finished and the living body is judged to be the living body, face matching is carried out in an Annoy index mode, and then comparison and identity judgment are carried out. The method specifically comprises the following steps: and in the face matching, a plurality of binary tree structures are formed by the obtained face characteristic vectors in an Annoy mode, when the face identification needs to be carried out on the collected new characteristic vectors, the binary trees are only required to be traversed respectively to obtain the characteristic vectors closest to the target, and threshold control judgment is set, so that comparison and identity judgment are carried out. Thus, the task of face recognition can be completed.
The invention can easily find that the living body detection is carried out before the face recognition, and the face recognition is carried out only under the condition that the detection object is a living body, thereby improving the reliability and the safety of the face recognition by adding a layer of protection mechanism. In addition, when the living body detection is carried out, the method adopts the key points of the human eyes to judge the blink, the blink detection method avoids using an image processing technology, and the blink detection method can be realized only by calculating the length-width ratio of the key points of the human eyes.
Claims (6)
1. A face recognition method with a living body detection function is characterized by comprising the following steps:
(1) carrying out face detection on the acquired image by using image acquisition equipment, carrying out blink detection in a face area when a face is detected, and judging whether the detected face is a living body;
(2) and when the detected face is a living body, identifying the face by using the face identification model.
2. The face recognition method with a living body detection function according to claim 1, wherein in the step (1), when performing the blink detection, the eye region of the face is first acquired, and 6 face feature points are set around the eyeglass region in a clockwise manner with the left corner of the eye region as a starting point; and calculating the length-width ratio of the eyes based on the 6 facial feature points, and judging whether the eyes blink according to the change condition of the length-width ratio of the eyes.
3. The face recognition method with liveness detection function according to claim 2, wherein the eye aspect ratio is calculated in such a manner thatWherein p is1Is the position of the feature point of the left corner face of the eye region, p2Is the position of the top left feature point of the eye region, p3Is the position of the feature point of the upper right of the eye region, p4Is the position of the feature point of the right-angle face of the eye region, p5Is the position of the lower right feature point of the eye region, p6The position of the lower left hand feature point of the eye region.
4. The face recognition method with living body detection function according to claim 1, wherein the face recognition model in the step (2) adopts MTCNN for face detection and cropping; the MTCNN is a cascade structure of three parts, wherein the first part is used for generating a candidate frame possibly having a face, the second part is used for taking the result of the first part as input, removing part of the candidate frame according to a non-maximum suppression method, and the third part is used for taking the result of the second part as input, further screening the candidate frame to obtain an accurate candidate frame and outputting face key points.
5. The method for recognizing a human face with a living body detection function according to claim 1, wherein during the training of the human face recognition model in the step (2), the cut image with the human face frame and the human face key point is sent to a pre-trained deep Facenet human face recognition neural network, and the pre-trained model is adopted to realize the training of the human face recognition model.
6. The face recognition method with a living body detection function according to claim 1, wherein in the step (2), when face recognition is performed, face matching is performed in an Annoy index manner, in the face matching, a plurality of binary tree structures are formed by using the obtained face feature vectors in an Annoy manner, and when face recognition is required for a new collected feature vector, only the binary trees need to be traversed respectively to obtain a feature vector nearest to a target, and threshold control judgment is set, so that comparison and identity judgment are performed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910930008.0A CN110705454A (en) | 2019-09-29 | 2019-09-29 | Face recognition method with living body detection function |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910930008.0A CN110705454A (en) | 2019-09-29 | 2019-09-29 | Face recognition method with living body detection function |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110705454A true CN110705454A (en) | 2020-01-17 |
Family
ID=69196448
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910930008.0A Pending CN110705454A (en) | 2019-09-29 | 2019-09-29 | Face recognition method with living body detection function |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110705454A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111325185A (en) * | 2020-03-20 | 2020-06-23 | 上海看看智能科技有限公司 | Face fraud prevention method and system |
CN113052087A (en) * | 2021-03-29 | 2021-06-29 | 杭州京威盛智能科技有限公司 | Face recognition method based on YOLOV5 model |
CN113345177A (en) * | 2021-05-11 | 2021-09-03 | 深圳市海恒智能科技有限公司 | Self-service book borrowing and returning system based on face recognition |
CN113760097A (en) * | 2021-09-16 | 2021-12-07 | Oppo广东移动通信有限公司 | Method and device for controlling volume, terminal and computer readable storage medium |
WO2024045350A1 (en) * | 2022-08-29 | 2024-03-07 | 天翼数字生活科技有限公司 | Eye movement based liveness detection method and system based on deep learning |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107346422A (en) * | 2017-06-30 | 2017-11-14 | 成都大学 | A kind of living body faces recognition methods based on blink detection |
CN109003346A (en) * | 2018-07-13 | 2018-12-14 | 河海大学 | A kind of campus Work attendance method and its system based on face recognition technology |
CN109784313A (en) * | 2019-02-18 | 2019-05-21 | 上海骏聿数码科技有限公司 | A kind of blink detection method and device |
CN109840565A (en) * | 2019-01-31 | 2019-06-04 | 成都大学 | A kind of blink detection method based on eye contour feature point aspect ratio |
CN109948568A (en) * | 2019-03-26 | 2019-06-28 | 东华大学 | Embedded human face identifying system based on ARM microprocessor and deep learning |
-
2019
- 2019-09-29 CN CN201910930008.0A patent/CN110705454A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107346422A (en) * | 2017-06-30 | 2017-11-14 | 成都大学 | A kind of living body faces recognition methods based on blink detection |
CN109003346A (en) * | 2018-07-13 | 2018-12-14 | 河海大学 | A kind of campus Work attendance method and its system based on face recognition technology |
CN109840565A (en) * | 2019-01-31 | 2019-06-04 | 成都大学 | A kind of blink detection method based on eye contour feature point aspect ratio |
CN109784313A (en) * | 2019-02-18 | 2019-05-21 | 上海骏聿数码科技有限公司 | A kind of blink detection method and device |
CN109948568A (en) * | 2019-03-26 | 2019-06-28 | 东华大学 | Embedded human face identifying system based on ARM microprocessor and deep learning |
Non-Patent Citations (1)
Title |
---|
黄骏: "基于文本特征提取的相似科研项目文档检索系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111325185A (en) * | 2020-03-20 | 2020-06-23 | 上海看看智能科技有限公司 | Face fraud prevention method and system |
CN111325185B (en) * | 2020-03-20 | 2023-06-23 | 上海看看智能科技有限公司 | Face fraud prevention method and system |
CN113052087A (en) * | 2021-03-29 | 2021-06-29 | 杭州京威盛智能科技有限公司 | Face recognition method based on YOLOV5 model |
CN113345177A (en) * | 2021-05-11 | 2021-09-03 | 深圳市海恒智能科技有限公司 | Self-service book borrowing and returning system based on face recognition |
CN113760097A (en) * | 2021-09-16 | 2021-12-07 | Oppo广东移动通信有限公司 | Method and device for controlling volume, terminal and computer readable storage medium |
WO2024045350A1 (en) * | 2022-08-29 | 2024-03-07 | 天翼数字生活科技有限公司 | Eye movement based liveness detection method and system based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yuan et al. | Fingerprint liveness detection using an improved CNN with image scale equalization | |
CN110705454A (en) | Face recognition method with living body detection function | |
Ko et al. | A novel and efficient feature extraction method for iris recognition | |
KR101901591B1 (en) | Face recognition apparatus and control method for the same | |
US10922399B2 (en) | Authentication verification using soft biometric traits | |
CN108537131B (en) | Face recognition living body detection method based on face characteristic points and optical flow field | |
KR20190016733A (en) | Method for recognizing partial obscured face by specifying partial area based on facial feature point, recording medium and apparatus for performing the method | |
CN111344703A (en) | User authentication device and method based on iris recognition | |
CN110796101A (en) | Face recognition method and system of embedded platform | |
Paul et al. | Extraction of facial feature points using cumulative histogram | |
CN111862413A (en) | Method and system for realizing epidemic situation resistant non-contact multidimensional identity rapid identification | |
CN111178130A (en) | Face recognition method, system and readable storage medium based on deep learning | |
Das et al. | Multi-angle based lively sclera biometrics at a distance | |
CN113627256A (en) | Method and system for detecting counterfeit video based on blink synchronization and binocular movement detection | |
CN107862298B (en) | Winking living body detection method based on infrared camera device | |
CN100495427C (en) | Human ear detection under complex background and method for syncretizing various information | |
CN109003367A (en) | Control method and device, storage medium, the terminal of gate inhibition | |
RU2316051C2 (en) | Method and system for automatically checking presence of a living human face in biometric safety systems | |
CN114299569A (en) | Safe face authentication method based on eyeball motion | |
Mohamed et al. | Automated face recogntion system: Multi-input databases | |
Chu et al. | Study of eye blinking to improve face recognition for screen unlock on mobile devices | |
CN107977622A (en) | Eyes detection method based on pupil feature | |
CN110135362A (en) | A kind of fast face recognition method based under infrared camera | |
JP2022141940A (en) | Method and apparatus for detecting live face, electronic device, and storage medium | |
CN113553890A (en) | Multi-modal biological feature fusion method and device, storage medium and equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |