CN112861764B - Face recognition living body judging method - Google Patents
Face recognition living body judging method Download PDFInfo
- Publication number
- CN112861764B CN112861764B CN202110212407.0A CN202110212407A CN112861764B CN 112861764 B CN112861764 B CN 112861764B CN 202110212407 A CN202110212407 A CN 202110212407A CN 112861764 B CN112861764 B CN 112861764B
- Authority
- CN
- China
- Prior art keywords
- speckle
- face
- images
- image
- standard
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000000605 extraction Methods 0.000 claims description 7
- 238000001727 in vivo Methods 0.000 claims description 2
- 238000010521 absorption reaction Methods 0.000 abstract description 6
- 238000001514 detection method Methods 0.000 description 7
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 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
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a human face recognition living body judging method, which comprises the following steps: the laser projector projects laser to the face to be identified, and the laser forms speckle on the face to be identified; the infrared camera acquires a speckle image of the face to be identified and sends the speckle image of the face to be identified to the identification judging unit; after receiving the speckle image sent by the infrared camera, the identification judging unit identifies a face area in the speckle image; extracting images of all speckles in the face region; comparing all the extracted speckle images with the standard speckle images one by one, calculating the similarity of each speckle image and the standard speckle image, then calculating the average value of the similarity of all the speckle images, taking the average value of the similarity as a living body recognition score, and if the living body recognition score is larger than a set threshold value, considering the face to be recognized as the living body face. The invention can effectively distinguish the living human face or the non-living human face by utilizing the absorption characteristic of the laser speckle on the human face skin, and has simple algorithm.
Description
Technical Field
The invention belongs to the technical field of face recognition, and particularly relates to a method for judging whether a human body is a living body or not in a face recognition process.
Background
With the development and popularization of face recognition technology, more and more scenes need to use face recognition technology to recognize the identity of a person. However, some illegal persons can use pictures or videos or simulation head models to replace real persons to carry out face recognition, so that potential safety hazards exist in a face recognition system. And in the face recognition process, living body detection can judge whether the currently recognized face is a living body face or a face in a photo or a video or a simulated head model so as to ensure the safety of a face recognition system. At present, living body detection in the face recognition process is mainly based on RGB camera or infrared camera or depth camera information, but the living body detection technology can realize living body detection to a certain extent, but has the defects, such as insufficient prevention capability for high-definition photos and videos based on the technology of living body detection of faces on 2D images such as RGB images or infrared images; the 3D image obtained by the depth camera is used for living body detection, and although the attack of photos and videos can be prevented, the attack of the simulation head model cannot be prevented.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a method for judging living bodies in face recognition based on laser speckle.
The invention adopts the following technical scheme:
a face recognition living body judging method comprises the following steps:
s1, a laser projector projects laser onto a face to be identified, and the laser forms speckle on the face to be identified;
s2, the infrared camera acquires a speckle image of the face to be identified, and sends the speckle image of the face to be identified to the identification judging unit;
s3, after the identification judging unit receives the speckle image sent by the infrared camera, identifying a face area in the speckle image;
s4, extracting images of all speckles in the face area;
s5, comparing all extracted speckle images with the standard speckle images one by one, calculating the similarity of each speckle image and the standard speckle image, then calculating the average value of the similarity of all speckle images, taking the average value of the similarity as a living body identification score, and if the living body identification score is larger than a set threshold value, considering the face to be identified as the living body face.
Further, in step S4, when an image of a certain speckle is extracted from the face region, the sub-pixel coordinates of the center of the speckle are determined, and an image of a region of a set size centered on the center of the speckle is extracted.
Further, euclidean distance is used for representing the similarity between a certain speckle image and a standard speckle image.
Further, the similarity of a certain speckle image to a standard speckle image is equal to the negative value of the euclidean distance of the speckle image and the standard speckle image.
Furthermore, the standard speckle images are obtained by projecting laser to different faces at different angles and different distances by using a laser projector under different scenes, respectively carrying out speckle extraction on the face areas of the face images after the face images are acquired by an infrared camera, and calculating the average images of all the extracted speckle images, namely the standard speckle images.
Further, after step S4, the depth of all the speckle images is obtained by using the depth camera, in step S5, all the speckle images with depth information are compared with the standard speckle images corresponding to the depth in the standard speckle image set one by one, the similarity between the speckle images and the corresponding standard speckle images is calculated, and then the average value of the similarity between all the speckle images is calculated as the in-vivo recognition score.
Further, the standard speckle image set comprises a plurality of standard speckle images, each standard speckle image represents a certain depth interval, when similarity comparison is carried out, the standard speckle images corresponding to the depth interval are selected from the standard speckle image set for comparison according to the depth value of the speckle image, and the similarity between the speckle image and the standard speckle image of the depth interval is calculated.
Further, the standard speckle image in the standard speckle image set is obtained by the following method: under different scenes, laser is projected to different faces at different angles and different distances by using a laser projector, the face images are obtained by using an infrared camera, speckle extraction is carried out on face areas of the face images to obtain images of all speckles of the face areas, depth values of the speckle images are obtained by using a depth camera, the speckle images with different depth values are divided into corresponding depth intervals according to the depth values, and an average image of all the speckle images in each depth interval subset is calculated, namely a standard speckle image of the depth interval subset is stored in the standard speckle image set.
Compared with the prior art, the invention has the beneficial effects that: the invention uses the absorption characteristics of laser speckle on living skin and non-living skin to distinguish living or non-living body, in the face recognition process, the laser projector forms speckle on the face to be recognized and acquires all speckle images of the face region, calculates the similarity of the speckle images and standard speckle images, and uses the average value of the similarity of all speckle images as the living body recognition score to judge whether the face is a living body face. In the preferred technical scheme, the depth value of the speckle is obtained through the depth camera while the speckle is extracted, depth information is also introduced into the standard speckle image, an image set containing standard speckle images in different depth intervals is established, and the depth information is introduced during speckle comparison operation, so that the speckle can be compared with the standard speckle with similar depth, and the robustness and accuracy are greatly improved.
Drawings
FIG. 1 is a flow chart of embodiment 1 of the present invention;
FIG. 2 is an exemplary diagram of a speckle image;
FIG. 3 is a flow chart of embodiment 2 of the present invention;
fig. 4a and 4b are exemplary diagrams of speckle images of different depths, respectively.
Detailed Description
The invention will be further described with reference to the following specific embodiments.
When laser irradiates on an optically rough surface, the reflected light field formed has random spatial light intensity distribution and takes on a granular structure as a result of wavelet coherent superposition scattered by a large number of irregularly distributed surface elements on the surface, and the laser speckle effect is called. The human skin has remarkable characteristic on the absorption of laser speckles, and the absorption characteristic of laser on human face is remarkably different from the absorption characteristic of laser on non-living body, so that the basic idea of the invention is to distinguish living body or non-living body by utilizing the absorption characteristic of laser speckles on human face skin. In the face recognition process, a laser projector is used for projecting laser on a face to be recognized, the laser wavelength can be 850nm or 940nm, laser speckles are formed on the face to be recognized by the laser, then an infrared camera is used for acquiring a speckle image of the face to be recognized, and the speckle image is sent to a recognition judging unit for living body recognition. Because living skin has special absorbability to speckle, human skin can be distinguished from photos, videos, head models or other attack props. The process according to the invention is described in detail below with reference to the accompanying drawings.
Example 1
Fig. 1 is a flowchart of an embodiment of the present invention, and as shown in fig. 1, the face recognition living body judging method of the present embodiment includes the following steps:
s1, a laser projector projects laser onto a face to be identified, and the laser forms speckle on the face to be identified;
s2, the infrared camera acquires a speckle image of the face to be identified, and sends the speckle image of the face to be identified to the identification judging unit; as shown in fig. 2, one frame of image acquired by the infrared camera has a plurality of speckles thereon;
s3, after receiving the speckle image sent by the infrared camera, the identification judging unit detects the face area of the image to identify the face area in the speckle image, wherein the face area can be identified by adopting the existing methods, such as a face detection method based on a neural network, such as YOLO3, MCNN, fast-MCNN and the like, and the face area identification method is not an innovation point of the invention and is not repeated here;
s4, extracting all speckle images of a face area in the image, namely extracting each speckle of the face area, wherein after the sub-pixel coordinates of the speckle center are determined, the extracted speckle image is an image of an area with a set size by taking the speckle (the speckle center) as the center, the size of the extracted area (the image) can be set according to the requirement, and the speckle image can be extracted by using a corrosion expansion algorithm;
s5, comparing all extracted speckle images with the standard speckle images one by one, calculating the similarity of each speckle image and the standard speckle image, then calculating the average value of the similarity of all speckle images, taking the average value of the similarity as a living body identification score, and if the living body identification score is larger than a set threshold value, considering the face to be identified as the living body face. The threshold value is set to an empirical value, and can be set by combining the expected false recognition rate and the true person passing rate. For example, a test set with a large number, balanced positive and negative samples and wide scene coverage is preset, and the threshold is determined on the test set by considering the false recognition rate and the true person passing rate at the same time. The invention adopts Euclidean distance to represent the similarity between the speckle image and the standard speckle image, the smaller the Euclidean distance is, the smaller the image difference is, the larger the similarity is, the more the living body identification score is, so the similarity is equal to the negative value of the Euclidean distance between the speckle image and the standard speckle image, namely, the Euclidean distance is obtained and then multiplied by minus one.
The standard speckle images are obtained by projecting laser to different faces at different angles and different distances by using a laser projector under different scenes, acquiring the face images by using an infrared camera, carrying out speckle extraction on face areas of the face images respectively, and calculating average images (image average values) of all speckle images obtained by extraction, wherein the average images of all the speckle images are the standard speckle images.
Example 2
Fig. 3 is a flowchart of the present embodiment, and as shown in fig. 3, the difference between the present embodiment and embodiment 1 is that: after the face region extracts all the speckle images, a step of obtaining speckle depth is further included, in which the depth of all the speckle images is obtained by using a depth camera, then each speckle image with depth information is compared with the standard speckle image of the corresponding depth interval in the standard speckle image set one by one, the similarity is calculated, and then the average value of the similarity of all the speckle images is used as the living body recognition score. The standard speckle image set of the embodiment comprises a plurality of standard speckle images with depth information, the depth value of each standard speckle image is different, when similarity comparison is carried out, the standard speckle images in the corresponding depth interval are selected in the standard speckle image set for comparison according to the depth value of the speckle image, and the similarity between the speckle images and the standard speckle images in the depth interval is calculated. For example, the depth value of the speckle image to be compared is 18 cm, the standard speckle image with the depth range of 10-20 cm can be selected in the standard speckle image set for comparison, and the similarity of the two images is calculated. According to the embodiment, depth information is introduced into the speckle images, and a standard speckle image set containing standard speckle images with different depth ranges is established, so that the standard speckle images with corresponding depths are compared during comparison, the robustness of the algorithm is higher, and the safety is higher.
The standard speckle image of the embodiment has depth values, a certain standard speckle image can represent a standard speckle image of a certain depth interval according to actual conditions, firstly, a laser projector is used for projecting laser onto different faces at different angles and different distances under different scenes, then an infrared camera is used for acquiring the face images, speckle extraction is respectively carried out on the face areas of the face images to obtain speckle images of the face areas, a depth camera is used for acquiring the depth values of the speckle images, the speckle images of different depth values are divided into corresponding depth intervals according to the depth values, for example, the depth values of 0-100 cm are divided into a plurality of sections, for example, 5 sections, 1-20 cm, 21-40 cm, 41-60 cm, 61-80 cm and 81-100 cm, when the depth values of a certain speckle image are 18 cm, the speckle images are classified into subsets of depth intervals of 1-20 cm, when the depth values of a certain speckle image are 58 cm, the speckle images are classified into subsets of depth intervals, and all the speckle images classified into the standard speckle images in the standard intervals, and then all the speckle images in the standard intervals are classified into the average image subsets. When the speckles are compared, standard speckle images corresponding to the depth intervals can be compared so as to adapt to the speckles with different distances.
Various other corresponding changes and modifications will occur to those skilled in the art from the foregoing description and the accompanying drawings, and all such changes and modifications are intended to be included within the scope of the present invention as defined in the appended claims.
Claims (7)
1. The human face recognition living body judging method is characterized by comprising the following steps of:
s1, a laser projector projects laser onto a face to be identified, and the laser forms speckle on the face to be identified;
s2, the infrared camera acquires a speckle image of the face to be identified, and sends the speckle image of the face to be identified to the identification judging unit;
s3, after the identification judging unit receives the speckle image sent by the infrared camera, identifying a face area in the speckle image;
s4, extracting images of all speckles in the face area;
s5, comparing all extracted speckle images with the standard speckle images one by one, calculating the similarity of each speckle image and the standard speckle image, then calculating the average value of the similarity of all speckle images, taking the average value of the similarity as a living body recognition score, and if the living body recognition score is larger than a set threshold value, considering the face to be recognized as a living body face;
the standard speckle images are obtained by projecting laser to different faces at different angles and different distances by using a laser projector under different scenes, respectively carrying out speckle extraction on face areas of the face images after the face images are obtained by an infrared camera, and calculating average images of all extracted speckle images, namely the standard speckle images.
2. The face recognition living body judging method according to claim 1, characterized in that: in step S4, when an image of a certain speckle is extracted from a face region, the sub-pixel coordinates of the center of the speckle are determined, and an image of a region of a set size centered on the center of the speckle is extracted.
3. The face recognition living body judging method according to claim 1, characterized in that: and (5) using Euclidean distance to represent the similarity between a certain speckle image and a standard speckle image.
4. The face recognition living body judging method according to claim 3, characterized in that: the similarity of a certain speckle image to a standard speckle image is equal to the negative of the euclidean distance of the speckle image and the standard speckle image.
5. The face recognition living body judging method according to claim 1, characterized in that: after step S4, the depth of all the speckle images is obtained by using a depth camera, in step S5, all the speckle images with depth information are compared with the standard speckle images corresponding to the depth in the standard speckle image set one by one, the similarity between the speckle images and the corresponding standard speckle images is calculated, and then the average value of the similarity between all the speckle images is calculated as the in-vivo recognition score.
6. The face recognition living body judging method according to claim 5, characterized in that: and when the similarity comparison is carried out, the standard speckle images in the corresponding depth interval are selected from the standard speckle image set for comparison according to the depth value of the speckle image, and the similarity between the speckle image and the standard speckle image in the depth interval is calculated.
7. The face recognition living body judging method according to claim 5 or 6, characterized in that: the standard speckle image in the standard speckle image set is obtained by the following method: under different scenes, laser is projected to different faces at different angles and different distances by using a laser projector, the face images are obtained by using an infrared camera, speckle extraction is carried out on face areas of the face images to obtain images of all speckles of the face areas, depth values of the speckle images are obtained by using a depth camera, the speckle images with different depth values are divided into corresponding depth intervals according to the depth values, and an average image of all the speckle images in each depth interval subset is calculated, namely a standard speckle image of the depth interval subset is stored in the standard speckle image set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110212407.0A CN112861764B (en) | 2021-02-25 | 2021-02-25 | Face recognition living body judging method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110212407.0A CN112861764B (en) | 2021-02-25 | 2021-02-25 | Face recognition living body judging method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112861764A CN112861764A (en) | 2021-05-28 |
CN112861764B true CN112861764B (en) | 2023-12-08 |
Family
ID=75991415
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110212407.0A Active CN112861764B (en) | 2021-02-25 | 2021-02-25 | Face recognition living body judging method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112861764B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113705408B (en) * | 2021-08-21 | 2022-08-05 | 深圳市迪威泰实业有限公司 | Face living body detection method and system |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105389553A (en) * | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Living body detection method and apparatus |
CN107169483A (en) * | 2017-07-12 | 2017-09-15 | 深圳奥比中光科技有限公司 | Tasks carrying based on recognition of face |
CN107944435A (en) * | 2017-12-27 | 2018-04-20 | 广州图语信息科技有限公司 | Three-dimensional face recognition method and device and processing terminal |
KR20180056976A (en) * | 2016-11-21 | 2018-05-30 | 서강대학교산학협력단 | Speckle reduction method using the similar patches in ultrasound image and apparatus thereof |
CN108509857A (en) * | 2018-03-06 | 2018-09-07 | 达闼科技(北京)有限公司 | Human face in-vivo detection method, electronic equipment and computer program product |
CN109284597A (en) * | 2018-11-22 | 2019-01-29 | 北京旷视科技有限公司 | A kind of face unlocking method, device, electronic equipment and computer-readable medium |
CN109325460A (en) * | 2018-09-30 | 2019-02-12 | 华为技术有限公司 | A kind of face identification method, optical center scaling method and terminal |
CN109583304A (en) * | 2018-10-23 | 2019-04-05 | 宁波盈芯信息科技有限公司 | A kind of quick 3D face point cloud generation method and device based on structure optical mode group |
CN109948399A (en) * | 2017-12-20 | 2019-06-28 | 宁波盈芯信息科技有限公司 | A kind of the face method of payment and device of smart phone |
CN110047100A (en) * | 2019-04-01 | 2019-07-23 | 四川深瑞视科技有限公司 | Depth information detection method, apparatus and system |
CN111597933A (en) * | 2020-04-30 | 2020-08-28 | 北京的卢深视科技有限公司 | Face recognition method and device |
WO2020206666A1 (en) * | 2019-04-12 | 2020-10-15 | 深圳市汇顶科技股份有限公司 | Depth estimation method and apparatus employing speckle image and face recognition system |
CN112232324A (en) * | 2020-12-15 | 2021-01-15 | 杭州宇泛智能科技有限公司 | Face fake-verifying method and device, computer equipment and storage medium |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9131118B2 (en) * | 2012-11-14 | 2015-09-08 | Massachusetts Institute Of Technology | Laser speckle photography for surface tampering detection |
CN103839258A (en) * | 2014-02-13 | 2014-06-04 | 西安交通大学 | Depth perception method of binarized laser speckle images |
US9861319B2 (en) * | 2015-03-23 | 2018-01-09 | University Of Kentucky Research Foundation | Noncontact three-dimensional diffuse optical imaging of deep tissue blood flow distribution |
KR102560710B1 (en) * | 2016-08-24 | 2023-07-27 | 삼성전자주식회사 | Apparatus and method using optical speckle |
CN110049305B (en) * | 2017-12-18 | 2021-02-26 | 西安交通大学 | Self-correcting method and device for structured light depth camera of smart phone |
-
2021
- 2021-02-25 CN CN202110212407.0A patent/CN112861764B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105389553A (en) * | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Living body detection method and apparatus |
KR20180056976A (en) * | 2016-11-21 | 2018-05-30 | 서강대학교산학협력단 | Speckle reduction method using the similar patches in ultrasound image and apparatus thereof |
CN107169483A (en) * | 2017-07-12 | 2017-09-15 | 深圳奥比中光科技有限公司 | Tasks carrying based on recognition of face |
CN109948399A (en) * | 2017-12-20 | 2019-06-28 | 宁波盈芯信息科技有限公司 | A kind of the face method of payment and device of smart phone |
CN107944435A (en) * | 2017-12-27 | 2018-04-20 | 广州图语信息科技有限公司 | Three-dimensional face recognition method and device and processing terminal |
CN108509857A (en) * | 2018-03-06 | 2018-09-07 | 达闼科技(北京)有限公司 | Human face in-vivo detection method, electronic equipment and computer program product |
CN109325460A (en) * | 2018-09-30 | 2019-02-12 | 华为技术有限公司 | A kind of face identification method, optical center scaling method and terminal |
CN109583304A (en) * | 2018-10-23 | 2019-04-05 | 宁波盈芯信息科技有限公司 | A kind of quick 3D face point cloud generation method and device based on structure optical mode group |
CN109284597A (en) * | 2018-11-22 | 2019-01-29 | 北京旷视科技有限公司 | A kind of face unlocking method, device, electronic equipment and computer-readable medium |
CN110047100A (en) * | 2019-04-01 | 2019-07-23 | 四川深瑞视科技有限公司 | Depth information detection method, apparatus and system |
WO2020199563A1 (en) * | 2019-04-01 | 2020-10-08 | 四川深瑞视科技有限公司 | Method, device, and system for detecting depth information |
WO2020206666A1 (en) * | 2019-04-12 | 2020-10-15 | 深圳市汇顶科技股份有限公司 | Depth estimation method and apparatus employing speckle image and face recognition system |
CN111597933A (en) * | 2020-04-30 | 2020-08-28 | 北京的卢深视科技有限公司 | Face recognition method and device |
CN112232324A (en) * | 2020-12-15 | 2021-01-15 | 杭州宇泛智能科技有限公司 | Face fake-verifying method and device, computer equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
采用数字图像相关法的人体测量;梁瑜;梁晋;王晓光;刘喜;;长春理工大学学报(自然科学版)(02);第127-131页 * |
Also Published As
Publication number | Publication date |
---|---|
CN112861764A (en) | 2021-05-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105335722B (en) | Detection system and method based on depth image information | |
CN105740775B (en) | Three-dimensional face living body identification method and device | |
CN108764058B (en) | Double-camera face in-vivo detection method based on thermal imaging effect | |
WO2016149938A1 (en) | Video monitoring method, video monitoring system and computer program product | |
CN105940430B (en) | Personnel's method of counting and its device | |
CN106056079B (en) | A kind of occlusion detection method of image capture device and human face five-sense-organ | |
KR20200063292A (en) | Emotional recognition system and method based on face images | |
JP2017531883A (en) | Method and system for extracting main subject of image | |
CN109902604B (en) | High-safety face comparison system and method based on Feiteng platform | |
CN109389185B (en) | Video smoke identification method using three-dimensional convolutional neural network | |
CN113011385B (en) | Face silence living body detection method, face silence living body detection device, computer equipment and storage medium | |
CN104463869A (en) | Video flame image composite recognition method | |
CN112861764B (en) | Face recognition living body judging method | |
CN107862298B (en) | Winking living body detection method based on infrared camera device | |
CN111723656A (en) | Smoke detection method and device based on YOLO v3 and self-optimization | |
KR101270718B1 (en) | Video processing apparatus and method for detecting fire from video | |
CN113255542A (en) | Illegal object identity recognition method based on illegal behavior recognition | |
US7440636B2 (en) | Method and apparatus for image processing | |
KR100543706B1 (en) | Vision-based humanbeing detection method and apparatus | |
Rossi et al. | Dynamic fire 3D modeling using a real-time stereovision system | |
CN115830513A (en) | Method, device and system for determining image scene change and storage medium | |
Huang et al. | Whole-body detection, recognition and identification at altitude and range | |
Feng et al. | An adaptive background biased depth map hole-filling method for Kinect | |
Nanda et al. | A robust elliptical head tracker | |
Mishra et al. | Occlusion handling strategies for multiple moving object classification |
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 |