CN113591622A - Living body detection method and device - Google Patents
Living body detection method and device Download PDFInfo
- Publication number
- CN113591622A CN113591622A CN202110803625.1A CN202110803625A CN113591622A CN 113591622 A CN113591622 A CN 113591622A CN 202110803625 A CN202110803625 A CN 202110803625A CN 113591622 A CN113591622 A CN 113591622A
- Authority
- CN
- China
- Prior art keywords
- screenshot
- detection
- body detection
- end server
- face
- 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 161
- 238000005070 sampling Methods 0.000 claims abstract description 87
- 238000000034 method Methods 0.000 claims abstract description 41
- 238000001574 biopsy Methods 0.000 claims abstract description 31
- 230000001960 triggered effect Effects 0.000 claims abstract description 9
- 238000001727 in vivo Methods 0.000 claims description 10
- 230000002452 interceptive effect Effects 0.000 abstract description 2
- 238000013135 deep learning Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
- Studio Devices (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a method and a device for detecting a living body, which are used for acquiring a real-time video stream of a front camera of terminal equipment by responding to detection operation triggered by a user; performing face recognition on the real-time video stream, and performing screenshot sampling in the face recognition process to generate a screenshot sampling set; sending the screenshot sampling set to a back-end server so that the back-end server performs biopsy on the screenshot sampling set to generate a biopsy result; and acquiring the living body detection result from the back-end server. Compared with the prior art, the problems of high failure rate and high bandwidth cost caused by uploading of large video files are solved; the problem that real-time interactive information prompt cannot be made to a user in the video recording process is solved, and the living body detection efficiency is improved.
Description
Technical Field
The invention relates to the technical field of in-vivo detection, in particular to a method and a device for in-vivo detection.
Background
The existing H5 end live body detection scheme generally obtains a user to upload to an H5 webpage after manually recording a video by a camera application through the camera application of a front end calling system, or directly calls the video stored in a local album to upload to an H5 webpage, then uploads an obtained video file to a server end for live body detection, and returns a detection result, so far, in the process of calling the camera application to manually record the video to the webpage end, the prior art needs the user to manually click to start recording the video and finish recording the video, and cannot perform real-time video content analysis and interactive information prompt when recording the video, which causes certain inconvenience to the user, and simultaneously, because the video recording duration cannot be limited, the recorded video file is large, which causes the problems of slow uploading, high failure rate, poor experience, high bandwidth cost and the like, and the user is in the video recording stage, the method breaks away from the original service system interface, and jumps to the camera application interface of the system, so that the information between the two interfaces can not be communicated in real time, and the shot video is easy to cause that the video does not meet the requirements of the service system, thereby causing low detection efficiency.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: provides a living body detection method and a living body detection device, and improves the living body detection efficiency.
In order to solve the above technical problems, the present invention provides a method and an apparatus for detecting a living body, comprising:
responding to detection operation triggered by a user, and acquiring a real-time video stream of a front camera of the terminal equipment;
performing face recognition on the real-time video stream, and performing screenshot sampling in the face recognition process to generate a screenshot sampling set;
sending the screenshot sampling set to a back-end server so that the back-end server performs biopsy on the screenshot sampling set to generate a biopsy result;
and acquiring the living body detection result from the back-end server.
Further, the screenshot sampling is performed in the face recognition process, and specifically includes:
and when the real-time video stream is subjected to face recognition, capturing the video frames with the face similarity reaching the preset threshold value in the real-time video stream through the preset threshold value.
Further, the back-end server performs live body detection on the screenshot sampling set to generate a live body detection result, which specifically includes:
and the back-end server sequentially performs living body detection on the single screenshots in the screenshot sampling set, generates a living body detection result of the single screenshots, and traverses all the screenshots in the screenshot sampling set until the living body detection results of all the screenshots are generated.
Further, the back-end server performs live body detection on a single screenshot in the screenshot sampling set, specifically:
the back-end server carries out face detection on a single screenshot in the screenshot sampling set, wherein the face detection is used for carrying out positioning capture on the position of the face so as to judge whether the single screenshot contains the face;
and simultaneously, the back-end server performs anti-counterfeiting detection on the single screenshot in the screenshot sampling set, wherein the anti-counterfeiting detection is used for judging whether the single screenshot is from real shooting.
Further, the present invention provides a living body detection apparatus, comprising: the device comprises a video acquisition module, an identification module, a detection module and a result acquisition module;
the video acquisition module is used for responding to detection operation triggered by a user and acquiring real-time video stream of a front camera of the terminal equipment;
the identification module is used for carrying out face identification on the real-time video stream, and carrying out screenshot sampling in the face identification process to generate a screenshot sampling set;
the detection module is used for sending the screenshot sampling set to a back-end server so that the back-end server can carry out in-vivo detection on the screenshot sampling set to generate an in-vivo detection result;
the result acquisition module is used for acquiring the living body detection result from the back-end server.
Further, the recognition module performs screenshot sampling in the face recognition process, specifically:
and when the real-time video stream is subjected to face recognition, capturing the video frames with the face similarity reaching the preset threshold value in the real-time video stream through the preset threshold value.
Further, the detection module is configured to enable the back-end server to perform live detection on the screenshot sampling set, so as to generate a live detection result, and specifically includes:
and the back-end server sequentially performs living body detection on the single screenshots in the screenshot sampling set, generates a living body detection result of the single screenshots, and traverses all the screenshots in the screenshot sampling set until the living body detection results of all the screenshots are generated.
Further, the detection module is configured to enable the back-end server to perform live body detection on a single screenshot in the screenshot sampling set, and specifically includes:
the back-end server carries out face detection on a single screenshot in the screenshot sampling set, wherein the face detection is used for carrying out positioning capture on the position of the face so as to judge whether the single screenshot contains the face;
and simultaneously, the back-end server carries out anti-counterfeiting detection on the single screenshot in the screenshot sampling set, wherein the anti-counterfeiting detection is used for judging whether the single screenshot is from real shooting.
Compared with the prior art, the living body detection method and the living body detection device provided by the embodiment of the invention have the following beneficial effects:
the real-time video stream of the front camera of the terminal equipment is obtained by responding to the detection operation triggered by the user, so that the problems of high failure rate and high bandwidth cost caused by uploading of large video files are solved; performing face recognition on the real-time video stream at a front end, performing real-time information interaction, and performing screenshot sampling in the face recognition process to generate a screenshot sampling set, wherein the screenshot sampling set comprises a plurality of screenshots; and sending the screenshot sampling set to a back-end server so that the back-end server performs living body detection on the screenshot sampling set, namely performing living body detection on a plurality of screenshots to generate a living body detection result, and acquiring the living body detection result from the back-end server, so that the reliability of the living body detection result can be effectively enhanced.
Drawings
FIG. 1 is a schematic flow chart diagram illustrating one embodiment of a method for in vivo testing provided by the present invention;
FIG. 2 is a schematic diagram of a real-time video stream acquisition process according to an embodiment of the in-vivo detection method provided by the present invention;
FIG. 3 is a schematic view of a human face recognition process according to an embodiment of the living body detection method provided by the present invention;
FIG. 4 is a schematic diagram of a service prompt on a H5 page according to an embodiment of the liveness detection method provided by the present invention;
FIG. 5 is a schematic structural diagram of an embodiment of a biopsy device provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of a method for detecting a living body according to the present invention, as shown in fig. 1, the method includes steps 101-104, which are as follows:
step 101: and responding to the detection operation triggered by the user to acquire the real-time video stream of the front camera of the terminal equipment.
In this embodiment, when a user triggers a live detection operation of a browser H5 page, a terminal device establishes a connection relationship with an audio engine, a video engine, and a microphone/camera of the terminal device by calling a getUserMedia web-api interface implemented based on a WebRTC standard, and is used to obtain a picture taken by a front camera of the terminal device in real time, so as to obtain video stream data, as shown in fig. 2. The terminal equipment can be a mobile phone, a notebook, a desktop computer, an intelligent television, vehicle-mounted equipment, wearable equipment, industrial equipment and the like.
Step 102: and performing face recognition on the real-time video stream, and performing screenshot sampling in the face recognition process to generate a screenshot sampling set.
In the embodiment, after the terminal device acquires the video stream, face recognition is performed on the real-time video stream, a browser H5 page of the terminal device is mainly a face recognition module of a convolutional neural network architecture based on JS, and a face is recognized and positioned by a light, rapid and accurate face mark detector in the browser H5 page, so that whether a face appears in the video stream can be conveniently detected; in the process of performing real-time face recognition on a browser H5 page, as shown in fig. 3, inference prediction is performed first, whether a face appears in a video stream picture is determined, a result of inference is fed back to an interface, and feature information recognized by a video is fed back to a service application system by calling the interface, specifically: firstly, a service prompt is carried out on a user, namely, the user is ensured to be right opposite to a mobile phone, and the light is sufficient, as shown in a figure 4, when a face does not enter a picture, the service prompt is carried out on the user through a face recognition positioning function, namely, the user is required to move the face into a frame, as shown in a figure 4, if the face does not enter the picture for a long time, a positioning overtime time is added to the face recognition function of a browser H5 page, when the positioning time exceeds the positioning overtime time, the detection on the face is stopped in time, meanwhile, a service flow is interrupted, and after the face enters the picture, the service prompt is carried out through the face recognition positioning function, namely, the user is required to keep the posture inconvenient, so that the subsequent screenshot and frame taking sampling can be conveniently carried out on a video stream, as shown in a figure 4, wherein the words when the service prompt is carried out can be self-defined according to needs. In this embodiment, when face recognition is performed on a real-time video stream, a video frame in which the face similarity reaches a preset threshold Y in the real-time video stream is captured through the preset threshold Y. The value range of the preset threshold Y is 0-1, the larger the value of Y is, the higher the probability of representing a face in a video frame is, and the preset threshold Y may be set autonomously according to the requirement, in this embodiment, the default of the preset threshold Y is set to 0.9. In the process of screenshot frame taking and sampling, different time intervals are set mainly through a random algorithm, video streams under the different time intervals are identified according to the face similarity, video frames at different time points reaching a preset threshold value Y are intercepted, a screenshot sampling set with a plurality of video frames with the face similarity reaching a preset Y value is generated, and the living body reliability can be effectively enhanced through random screenshot sampling.
Step 103: and sending the screenshot sampling set to a back-end server so that the back-end server performs biopsy on the screenshot sampling set to generate a biopsy result.
In the embodiment, after a plurality of pictures are successfully collected by the terminal equipment, the data of the screenshot sampling set is transmitted to the back-end server for subsequent detection by calling an HTTPS interface provided by the back-end server, specifically, in the process of performing the in-vivo detection on single screenshots in the screenshot sampling set, the back-end server obtains the characteristics and the difference of a living body and a non-living body through a deep learning method, then performs face detection on the single screenshots, namely, positioning and capturing the positions of the faces, estimates the size of the faces according to the characteristic values of the living body and the non-living body obtained through the deep learning, and then performs segmentation to judge whether the single screenshots contain the faces; then, carrying out anti-counterfeiting detection through the single screenshot, and judging whether the face in the single screenshot is from real shooting or not according to the characteristics and difference of the living body and the non-living body obtained in a deep learning mode; the anti-counterfeiting detection is carried out on the single screenshot, so that the attacks of screen reproduction, video playback, buttonhole/buttonhole attacks, photo/high-definition poster reproduction, headgear/mask tools and the like can be effectively prevented; after a single screenshot is subjected to biopsy, generating a biopsy result corresponding to the single screenshot, then sequentially carrying out biopsy on other single screenshots in the screenshot sampling set until all photos of the screenshot sampling set are traversed, in the process, carrying out multiple human face detection and anti-counterfeiting detection judgments on the screenshot sampling set, and finally generating the biopsy results of all the screenshots, wherein the detection results have two possibilities, one is that the detection is passed, and the other is not; in this embodiment, different from a network environment where a larger traffic bandwidth is occupied and a stable network environment is needed for directly transmitting a video or a video stream in the conventional H5 live body detection, the technical scheme only needs to transmit a photo, and has a higher success rate in a scene with a poor network environment.
Step 104: and obtaining the living body detection result from the back-end server.
In this embodiment, an H5 biopsy page of the terminal device obtains a biopsy result from the backend server, where the biopsy result is an overall detection result of the screenshot sample set, and in this embodiment, when all the biopsy results of all the screenshots in the screenshot sample set in step 103 pass the detection, the biopsy result of the backend server obtained by the H5 biopsy page of the terminal device is a biopsy, and a prompt of "successful detection" is sent to the user detection end, as shown in fig. 4 (a); on the contrary, if the live body detection result of a part of the screenshots in the live body detection results of all the screenshots in the screenshot sampling set in the step 103 is that the detection fails, the live body detection result of the back-end server acquired by the terminal device H5 live body detection page is a non-live body, and a prompt of 'detection failure, please detect again' is sent to the user detection end method, and the step 101 is returned for re-detection, so that the method can effectively enhance the reliability of the live body.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an embodiment of a living body detection apparatus provided by the present invention, as shown in fig. 5, the structure includes a video acquisition module 401, an identification module 402, a detection module 403, and a result acquisition module 404;
the video acquiring module 401 is configured to respond to a detection operation triggered by a user to acquire a real-time video stream of a front-facing camera of a terminal device. In this embodiment, when a user triggers a live detection operation of a browser H5 page, a terminal device establishes a connection relationship with an audio engine, a video engine, and a microphone/camera of the terminal device by calling a getUserMedia web-api interface implemented based on a WebRTC standard, and is configured to acquire a picture taken by a front camera of the terminal device in real time to obtain video stream data. The terminal equipment can be a mobile phone, a notebook, a desktop computer, an intelligent television, vehicle-mounted equipment, wearable equipment, industrial equipment and the like.
The recognition module 402 is configured to perform face recognition on the real-time video stream, perform screenshot sampling in the face recognition process, and generate a screenshot sampling set. In the embodiment, after the terminal device acquires the video stream, face recognition is performed on the real-time video stream, a browser H5 page of the terminal device is mainly a face recognition module of a convolutional neural network architecture based on JS, and a face is recognized and positioned by a light, rapid and accurate face mark detector in the browser H5 page, so that whether a face appears in the video stream can be conveniently detected; in the process of carrying out real-time face recognition on a browser H5 page, reasoning and predicting are firstly carried out, whether a face appears in a video stream picture or not is judged, a presumed result is fed back to an interface, and characteristic information recognized by a video is fed back to a service application system by calling the interface, wherein the method specifically comprises the following steps: firstly, service prompting is carried out on a user, namely, the user is ensured to be right opposite to a mobile phone and the light is sufficient, when a face does not enter a picture, service prompting is carried out on the user through a face recognition positioning function, namely, the user is required to move the face into a frame, if the face does not enter the picture for a long time, positioning overtime is added to the face recognition function of a browser H5 page, when the positioning time exceeds the positioning overtime, the detection of the face is stopped in time, meanwhile, the service flow is interrupted, when the face enters the picture, service prompting is carried out through the face recognition positioning function, namely, the user is required to keep the posture inconvenient, and subsequent screenshot and frame taking sampling of a video stream are facilitated, wherein words in the service prompting process can be customized according to needs. In this embodiment, when face recognition is performed on a real-time video stream, a video frame in which the face similarity reaches a preset threshold Y in the real-time video stream is captured through the preset threshold Y, wherein a value range of the preset threshold Y is 0-1, the larger the Y value is, the higher the probability that a face is represented in the video frame is, and the preset threshold Y may be autonomously set according to a requirement, in this embodiment, the default setting of the preset threshold Y is 0.9. In the process of screenshot frame taking and sampling, video streams with different time interval lengths are taken out mainly through a random algorithm, the video streams with different time intervals are intercepted according to the face similarity, the video frames of different time points reaching a preset threshold value Y are intercepted, and a screenshot sampling set with a plurality of video frames with the face similarity reaching a preset Y value is generated.
The detection module 403 is configured to send the screenshot sampling set to the backend server, so that the backend server performs live detection on the screenshot sampling set to generate a live detection result. In the embodiment, after the terminal device collects a plurality of photos successfully, the data of the screenshot sampling set is transmitted to the back-end server by calling the HTTPS interface provided by the back-end server, used for subsequent detection, in particular, a back-end server is used for carrying out living body detection on single screenshots in a screenshot sampling set in sequence, in the process of living body detection, the back-end server obtains the characteristics and the difference of the living body and the non-living body through a deep learning method, then carries out face detection on a single screenshot, namely positioning and capturing the position of the human face, estimating the size of the human face according to the characteristic values of living bodies and non-living bodies obtained by deep learning, then, segmentation is carried out to judge whether a single screenshot contains a human face, anti-counterfeiting detection is carried out through the single screenshot, and whether the human face in the single screenshot is from real shooting is judged according to the characteristics and the difference of a living body and a non-living body obtained in a deep learning mode; the anti-counterfeiting detection is carried out on the single screenshot, so that the attacks of screen reproduction, video playback, buttonhole/buttonhole attacks, photo/high-definition poster reproduction, headgear/mask tools and the like can be effectively prevented; after a single screenshot is subjected to biopsy, generating a biopsy result corresponding to the single screenshot, then sequentially carrying out biopsy on other single screenshots in the screenshot sampling set until all photos of the screenshot sampling set are traversed, in the process, carrying out multiple human face detection and anti-counterfeiting detection judgments on the screenshot sampling set, and finally generating the biopsy results of all the screenshots, wherein the detection results have two possibilities, one is that the detection is passed, and the other is not; in this embodiment, different from a network environment where a larger traffic bandwidth is occupied and a stable network environment is needed for directly transmitting a video or a video stream in the conventional H5 live body detection, the technical scheme only needs to transmit a photo, and has a higher success rate in a scene with a poor network environment.
The result obtaining module 404 is configured to obtain the living body detection result from the backend server. In this embodiment, an H5 biopsy page of the terminal device obtains a biopsy result from the backend server, where the biopsy result is an overall detection result of the screenshot sampling set, and in this embodiment, when all the biopsy results of all the screenshots in the screenshot sampling set in the detection module 403 pass the detection, the biopsy result of the backend server obtained by the H5 biopsy page of the terminal device is a biopsy, and a prompt of "successful detection" is sent to the user detection end; on the contrary, if the live body detection result of a partial screenshot exists in the live body detection results of all the screenshots in the screenshot sampling set in the detection module 403, the live body detection result of the back-end server acquired by the terminal device H5 live body detection page is a non-live body, and a prompt of "detection failure, please detect again" is sent to the user detection end method, and returned to the video acquisition module 401 for re-detection, which can effectively enhance the reliability of the live body.
In conclusion, the live body detection method and the live body detection device obtain the real-time video stream of the front camera of the terminal equipment by responding to the detection operation triggered by the user, and avoid the problems of high failure rate and high bandwidth cost caused by uploading of large video files; performing face recognition on a real-time video stream at a front end, performing real-time information interaction, and performing screenshot sampling in the face recognition process to generate a screenshot sampling set, wherein the screenshot sampling set comprises a plurality of screenshots; the screenshot sampling set is sent to the back-end server, so that the back-end server performs live body detection on the screenshot sampling set, namely, live body detection is performed on a plurality of screenshots to generate a live body detection result, the live body detection result is obtained from the back-end server, and the reliability of the live body detection result and the live body detection efficiency can be effectively enhanced.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and substitutions can be made without departing from the technical principle of the present invention, and these modifications and substitutions should also be regarded as the protection scope of the present invention.
Claims (8)
1. A method of in vivo detection, comprising:
responding to detection operation triggered by a user, and acquiring a real-time video stream of a front camera of the terminal equipment;
performing face recognition on the real-time video stream, and performing screenshot sampling in the face recognition process to generate a screenshot sampling set;
sending the screenshot sampling set to a back-end server so that the back-end server performs biopsy on the screenshot sampling set to generate a biopsy result;
and acquiring the living body detection result from the back-end server.
2. The method for detecting a living body according to claim 1, wherein the screenshot sampling is performed in a face recognition process, and specifically comprises:
and when the real-time video stream is subjected to face recognition, capturing the video frames with the face similarity reaching the preset threshold value in the real-time video stream through the preset threshold value.
3. The live body detection method according to claim 1, wherein the back-end server performs live body detection on the screenshot sampling set to generate a live body detection result, specifically:
and the back-end server sequentially performs living body detection on the single screenshots in the screenshot sampling set, generates a living body detection result of the single screenshots, and traverses all the screenshots in the screenshot sampling set until the living body detection results of all the screenshots are generated.
4. The live body detection method according to claim 3, wherein the back-end server performs live body detection on a single screenshot in the screenshot sampling set, specifically:
the back-end server carries out face detection on a single screenshot in the screenshot sampling set, wherein the face detection is used for carrying out positioning capture on the position of the face so as to judge whether the single screenshot contains the face;
and simultaneously, the back-end server performs anti-counterfeiting detection on the single screenshot in the screenshot sampling set, wherein the anti-counterfeiting detection is used for judging whether the single screenshot is from real shooting.
5. A living body detection device, comprising: the device comprises a video acquisition module, an identification module, a detection module and a result acquisition module;
the video acquisition module is used for responding to detection operation triggered by a user and acquiring real-time video stream of a front camera of the terminal equipment;
the identification module is used for carrying out face identification on the real-time video stream, and carrying out screenshot sampling in the face identification process to generate a screenshot sampling set;
the detection module is used for sending the screenshot sampling set to a back-end server so that the back-end server can carry out in-vivo detection on the screenshot sampling set to generate an in-vivo detection result;
the result acquisition module is used for acquiring the living body detection result from the back-end server.
6. The living body detection apparatus as claimed in claim 5, wherein the recognition module performs screenshot sampling in a face recognition process, specifically:
and when the real-time video stream is subjected to face recognition, capturing the video frames with the face similarity reaching the preset threshold value in the real-time video stream through the preset threshold value.
7. The live body detection device of claim 5, wherein the detection module is configured to enable a back-end server to perform live body detection on the screenshot sampling set to generate a live body detection result, and specifically:
and the back-end server sequentially performs living body detection on the single screenshots in the screenshot sampling set, generates a living body detection result of the single screenshots, and traverses all the screenshots in the screenshot sampling set until the living body detection results of all the screenshots are generated.
8. The live body detection device of claim 7, wherein the detection module is configured to enable the back-end server to perform live body detection on a single screenshot in the screenshot sampling set, specifically:
the back-end server carries out face detection on a single screenshot in the screenshot sampling set, wherein the face detection is used for carrying out positioning capture on the position of the face so as to judge whether the single screenshot contains the face;
and simultaneously, the back-end server carries out anti-counterfeiting detection on the single screenshot in the screenshot sampling set, wherein the anti-counterfeiting detection is used for judging whether the single screenshot is from real shooting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110803625.1A CN113591622A (en) | 2021-07-15 | 2021-07-15 | Living body detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110803625.1A CN113591622A (en) | 2021-07-15 | 2021-07-15 | Living body detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113591622A true CN113591622A (en) | 2021-11-02 |
Family
ID=78247720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110803625.1A Pending CN113591622A (en) | 2021-07-15 | 2021-07-15 | Living body detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113591622A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550671A (en) * | 2016-01-28 | 2016-05-04 | 北京麦芯科技有限公司 | Face recognition method and device |
| CN108124486A (en) * | 2017-12-28 | 2018-06-05 | 深圳前海达闼云端智能科技有限公司 | Face living body detection method based on cloud, electronic device and program product |
| CN108491784A (en) * | 2018-03-16 | 2018-09-04 | 南京邮电大学 | The identification in real time of single feature towards large-scale live scene and automatic screenshot method |
| CN108960205A (en) * | 2018-08-06 | 2018-12-07 | 广州开瑞信息科技有限公司 | A kind of Intelligent human-face recognition methods and system |
| WO2020168960A1 (en) * | 2019-02-19 | 2020-08-27 | 杭州海康威视数字技术股份有限公司 | Video analysis method and apparatus |
| CN111860455A (en) * | 2020-08-04 | 2020-10-30 | 中国银行股份有限公司 | Living body detection method and device based on HTML5 page |
| CN112307817A (en) * | 2019-07-29 | 2021-02-02 | 中国移动通信集团浙江有限公司 | Face living body detection method and device, computing equipment and computer storage medium |
| CN112507798A (en) * | 2020-11-12 | 2021-03-16 | 上海优扬新媒信息技术有限公司 | Living body detection method, electronic device, and storage medium |
-
2021
- 2021-07-15 CN CN202110803625.1A patent/CN113591622A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550671A (en) * | 2016-01-28 | 2016-05-04 | 北京麦芯科技有限公司 | Face recognition method and device |
| CN108124486A (en) * | 2017-12-28 | 2018-06-05 | 深圳前海达闼云端智能科技有限公司 | Face living body detection method based on cloud, electronic device and program product |
| CN108491784A (en) * | 2018-03-16 | 2018-09-04 | 南京邮电大学 | The identification in real time of single feature towards large-scale live scene and automatic screenshot method |
| CN108960205A (en) * | 2018-08-06 | 2018-12-07 | 广州开瑞信息科技有限公司 | A kind of Intelligent human-face recognition methods and system |
| WO2020168960A1 (en) * | 2019-02-19 | 2020-08-27 | 杭州海康威视数字技术股份有限公司 | Video analysis method and apparatus |
| CN112307817A (en) * | 2019-07-29 | 2021-02-02 | 中国移动通信集团浙江有限公司 | Face living body detection method and device, computing equipment and computer storage medium |
| CN111860455A (en) * | 2020-08-04 | 2020-10-30 | 中国银行股份有限公司 | Living body detection method and device based on HTML5 page |
| CN112507798A (en) * | 2020-11-12 | 2021-03-16 | 上海优扬新媒信息技术有限公司 | Living body detection method, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8314854B2 (en) | Apparatus and method for image recognition of facial areas in photographic images from a digital camera | |
| US7630561B2 (en) | Image processing | |
| WO2017041366A1 (en) | Method and device for image recognition | |
| JP2022545899A (en) | Categorization method and apparatus, electronic device, storage medium, and computer program | |
| KR20100102700A (en) | Digital camera focusing using stored object recognition | |
| US20050265581A1 (en) | Object detection | |
| CN103581705A (en) | Method and system for recognizing video program | |
| US20230360437A1 (en) | Training system and data collection device | |
| CN103905710A (en) | Image capture method, and mobile terminal and device thereof | |
| CN109697389B (en) | Identity recognition method and device | |
| CN113591622A (en) | Living body detection method and device | |
| CN101753854A (en) | Image communication method and electronic device using same | |
| CN105718160A (en) | Application operation triggering method, apparatus and system | |
| CN113506320B (en) | Image processing method and device, electronic equipment and storage medium | |
| KR102456189B1 (en) | system for Cloud edge-based video analysis | |
| CN113259734B (en) | Intelligent broadcasting guide method, device, terminal and storage medium for interactive scene | |
| WO2021129444A1 (en) | File clustering method and apparatus, and storage medium and electronic device | |
| CN112511786A (en) | Method and device for adjusting volume of video conference, terminal equipment and storage medium | |
| CN113542604A (en) | Video focusing method and device | |
| CN113762156B (en) | Video data processing method, device and storage medium | |
| CN118075418B (en) | Video conference content output optimization method, device, equipment and storage medium thereof | |
| WO2022156294A1 (en) | Video processing method and apparatus, computer readable storage medium, and electronic device | |
| CN113506319B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN112437279B (en) | Video analysis method and device | |
| TWI857242B (en) | Optical flow information prediction method, device, electronic equipment and storage medium |
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 |