CN111310567A - Face recognition method and device under multi-person scene - Google Patents
Face recognition method and device under multi-person scene Download PDFInfo
- Publication number
- CN111310567A CN111310567A CN202010046859.1A CN202010046859A CN111310567A CN 111310567 A CN111310567 A CN 111310567A CN 202010046859 A CN202010046859 A CN 202010046859A CN 111310567 A CN111310567 A CN 111310567A
- Authority
- CN
- China
- Prior art keywords
- person
- human body
- face recognition
- face
- layering
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/647—Three-dimensional objects by matching two-dimensional images to three-dimensional objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a face recognition method and a face recognition device in a multi-person scene, wherein the face recognition method in the multi-person scene comprises the following steps: carrying out pattern recognition on the pre-generated multi-person picture to separate out a plurality of human body pictures; scanning a shot object to generate a 3D oscillogram; and layering the 3D oscillogram according to the shooting distance, and comparing a layering result with the plurality of human body pictures to identify the human face. The face recognition method under the multi-person scene determines the positions and distances of the shooting field personnel through scanning, accurately captures the images of the personnel closest to the central area of the camera, and effectively solves the problem of capture failure or errors caused by the fact that the face images of the rear personnel are too large.
Description
Technical Field
The invention relates to the technical field of financial institution client identity confirmation, in particular to a face recognition method and device in a multi-person scene.
Background
At present, technologies of face brushing verification and face brushing consumption are developing vigorously, and bring much convenience and new experience to users. However, as a new technology, there are many defects and risks, one of which is how to accurately position a face grabbed by a client when a plurality of faces appear in a shot, for example, when there are a plurality of people near the shot, the prior art often takes a face with the largest search area (pixels) in the shot range as the face of the client to take a picture (the largest face takes precedence), which is more likely to cause a problem of a deduction error due to a wrong picture, and particularly, when the face of the client is small, and the face of surrounding people is large, it is very likely to make a mistake, and meanwhile, a possible opportunity is brought to some illegal persons.
Disclosure of Invention
Aiming at the problems in the prior art, the face recognition method under the multi-person scene determines the positions and distances of shooting field personnel through scanning, accurately captures the images of the personnel closest to the central area of the camera, and effectively solves the problem of capture failure or errors caused by the fact that the face images of the rear personnel are too large.
In order to solve the technical problems, the invention provides the following technical scheme:
in a first aspect, the present invention provides a face recognition method in a multi-person scene, including:
carrying out pattern recognition on the pre-generated multi-person picture to separate out a plurality of human body pictures;
scanning a shot object to generate a 3D oscillogram;
and layering the 3D oscillogram according to the shooting distance, and comparing a layering result with the plurality of human body pictures to identify the human face.
In one embodiment, the step of generating the photos of the plurality of persons comprises:
and shooting the multi-person scene to generate a multi-person picture.
In an embodiment, the layering the 3D oscillogram according to the shooting distance and comparing the layering result with the plurality of human body pictures to identify the human face includes:
layering the 3D oscillogram according to a preset distance unit to generate layered images with different shooting distances;
comparing the plurality of human body pictures with the layered image to determine a layer of each photographed person in the plurality of persons in the layered image;
determining the shooting distance of each shot person according to the layer of each shot person in the layered image;
and carrying out face recognition according to the shooting distance.
In an embodiment, the human body pictures include human body contours and human faces, and the comparing the plurality of human body pictures with the layered images includes:
determining the positions of the human body outlines in the human body pictures;
and comparing the human body pictures with the layered images according to the positions.
In one embodiment, the method for scanning the plurality of human body pictures includes: radar, sonar, laser, and infrared scanning.
In a second aspect, the present invention provides a face recognition apparatus in a multi-person scene, the apparatus comprising:
the photo recognition unit is used for carrying out image recognition on the pre-generated multi-person photo so as to separate a plurality of human body pictures;
the picture scanning unit is used for scanning the shot person to generate a 3D oscillogram;
and the oscillogram layering unit is used for layering the 3D oscillogram according to the shooting distance and comparing the layering result with the human body pictures so as to identify the human face.
In an embodiment, the face recognition apparatus in a multi-person scene further includes: the photo generation unit is used for generating the multi-person photo, and the photo generation unit is specifically used for shooting the multi-person scene so as to generate the multi-person photo.
In one embodiment, the oscillogram layering unit includes:
the layering module is used for layering the 3D oscillogram according to a preset distance unit so as to generate layered images with different shooting distances;
the comparison module is used for comparing the human body pictures with the layered images so as to determine the layer of each photographed person in the layered images;
the distance determining module is used for determining the shooting distance of each shot person according to the layer of each shot person in the layered image;
and the face recognition module is used for carrying out face recognition according to the shooting distance.
In one embodiment, the human body picture includes a human body contour and a human face, and the comparison module includes:
the position determining module is used for determining the positions of the human body outlines in the human body pictures;
and the comparison module is used for comparing the human body pictures with the layered images according to the positions.
In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the face recognition method in a multi-person scenario when executing the computer program.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method of face recognition in a multi-person scenario.
As can be seen from the above description, embodiments of the present invention provide a method and an apparatus for face recognition in a multi-person scene, where a radar scanning device is configured on a camera or other shooting devices to generate a stereoscopic layer layered according to distance, and then the stereoscopic layer is compared with a shape of a person identified and separated from a picture to calculate distances between different persons in the picture and the camera, and then a person closest to the distance is selected to capture a face picture of the person, which is used as an object target for face recognition. The invention comprehensively utilizes the spatial distance difference of the client, accurately positions and captures, and solves the problems that the positioning cannot be carried out or the capturing is wrong in a multi-person scene, and the traditional face screening mode only considers the face area of the photo, so that the positioning failure or the capturing error is easy to occur because the face of the client is small and the interference of the face of the person is large.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a first flowchart illustrating a face recognition method in a multi-person scene according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a face recognition method in a multi-person scene in an embodiment of the present invention;
FIG. 3 is a flowchart illustrating steps 300 of a face recognition method in a multi-person scenario according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a step 302 of a face recognition method in a multi-person scenario according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart of a face recognition method in a multi-person scenario in an embodiment of the present invention;
fig. 6 is a first block diagram illustrating a structure of a face recognition apparatus in a multi-person scene according to an embodiment of the present invention;
fig. 7 is a structural block diagram of a face recognition apparatus in a multi-person scene in an embodiment of the present invention;
FIG. 8 is a block diagram of a waveform diagram hierarchical cell structure in an embodiment of the present invention;
FIG. 9 is a block diagram of a comparison module in an embodiment of the invention;
fig. 10 is a schematic structural diagram of an electronic device in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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.
Based on the disadvantages of the prior art, an embodiment of the present invention provides a specific implementation of a face recognition method in a multi-person scene, and referring to fig. 1, the method specifically includes the following steps:
step 100: and carrying out pattern recognition on the pre-generated multi-person picture so as to separate a plurality of human body pictures.
Specifically, the pre-generated multi-person photo is subjected to pattern recognition, and a human body picture in a central area is separated and comprises a human face and a human body outline. For example: if there are three main people in the multi-person photo, 3 body pictures are generated.
Step 200: the subject is scanned to generate a 3D waveform map.
In an embodiment, a radar scanning device may be disposed at the shooting device, and the shooting device scans the photographer to generate a 3D oscillogram of radar emission waves, and of course, sonar, laser, infrared scanning, and the like may be used instead of the radar scanning device, which is not limited in this embodiment.
Step 300: and layering the 3D oscillogram according to the shooting distance, and comparing a layering result with the plurality of human body pictures to identify the human face.
It can be understood that by comparing the layering result of the 3D oscillogram with a plurality of human body pictures, the photographer closest to the image pickup device can be determined, and thus the photographing object can be accurately found.
As can be seen from the above description, the embodiment of the present invention provides a method for recognizing a face in a multi-person scene, where a radar scanning device is configured on a camera or other shooting devices to generate a stereoscopic layer layered according to distance, and then the stereoscopic layer is compared with a shape of a person recognized and separated from a picture to calculate distances between different persons in the picture and the camera, and then the person closest to the distance is selected to intercept the face picture, which is used as an object target for face recognition. The invention comprehensively utilizes the spatial distance difference of the client, accurately positions and captures, and solves the problems that the positioning cannot be carried out or the capturing is wrong in a multi-person scene, and the traditional face screening mode only considers the face area of the photo, so that the positioning failure or the capturing error is easy to occur because the face of the client is small and the interference of the face of the person is large.
In an embodiment, referring to fig. 2, the face recognition method in a multi-person scene further includes:
step 400: and generating the multi-person photo.
Further, step 400 is specifically to shoot the multi-person scene to generate a multi-person photo.
It will be appreciated that the camera may be a monocular camera or a binocular camera to generate a clearer picture of multiple persons.
In one embodiment, referring to FIG. 3, step 300 comprises:
step 301: and layering the 3D oscillogram according to a preset distance unit to generate layered images with different shooting distances.
In one embodiment, the preset distance in step 301 may be set to 30cm, which is the thickness of the body of an ordinary person, so as to ensure that different human bodies can be distinguished.
Step 302: and comparing the plurality of human body pictures with the layered image to determine the layer of each photographed person in the plurality of persons in the layered image.
Specifically, the human body contour map of each human body photo (only one human body contour map exists in one human body photo) is sequentially compared with the layered images of the 3D oscillogram, and the layer where each photographed person is located is determined.
Step 303: and determining the shooting distance of each shot object according to the layer of each shot object in the layered image.
Step 304: and carrying out face recognition according to the shooting distance.
It can be understood that the person to be photographed corresponding to the shortest human body contour map in the photographing distance determined in the step 303 is selected, and the person to be photographed is the target person to be photographed.
In one embodiment, the human body picture comprises a human body outline and a human face. Referring to fig. 4, step 302: the method comprises the following steps:
step 3021: and determining the positions of the human body outlines in the human body pictures.
Step 3022: and comparing the human body pictures with the layered images according to the positions.
In step 3021 and step 3022, specifically, the profile of each subject in the photograph is sequentially compared with the layered images of the radar 3D waveform image, and the layer in which each subject is located is determined. And in the comparison process, the position of the human body contour map in the shot picture is combined, and the corresponding area of the radar graph is searched and matched, so that the accuracy is improved.
In one embodiment, the method for scanning the subject includes: radar, sonar, laser, and infrared scanning.
It can be understood that the face recognition method in the multi-person scene of the embodiment can also be implemented by the following method: the human body closest to the shooting device is determined by using devices such as radar or sonar, laser, infrared scanning and the like, and then the human face picture of the human body is shot and intercepted by the camera.
As can be seen from the above description, the embodiment of the present invention provides a method for recognizing a face in a multi-person scene, where a radar scanning device is configured on a camera or other shooting devices to generate a stereoscopic layer layered according to distance, and then the stereoscopic layer is compared with a shape of a person recognized and separated from a picture to calculate distances between different persons in the picture and the camera, and then the person closest to the distance is selected to intercept the face picture, which is used as an object target for face recognition. The invention comprehensively utilizes the spatial distance difference of the client, accurately positions and captures, and solves the problems that the positioning cannot be carried out or the capturing is wrong in a multi-person scene, and the traditional face screening mode only considers the face area of the photo, so that the positioning failure or the capturing error is easy to occur because the face of the client is small and the interference of the face of the person is large.
To further explain the scheme, the present invention provides a specific application example of the face recognition method in a multi-person scene by face payment, and the specific application example specifically includes the following contents, see fig. 5.
S0: the camera takes a picture containing the main face in the central area of the current lens.
It is understood that the primary face contains at least a photograph of the payer's face.
S1: and carrying out pattern recognition on the picture, and separating a human body picture in the central area.
It can be understood that the human body picture includes a human face and a human body outline. If there are three main people in the photo, 3 pictures of the people are generated.
S2: the radar scanning device scans the area in front of the camera and generates a 3D graph of radar reflection waves.
Radar scanning can be replaced by sonar, laser, infrared scanning and other similar devices to generate a 3D image of the surrounding environment, and the final purpose is to determine the position and distance of people;
s3: layering the radar 3D waveform map by distance from near to far.
Step S3 is performed with a minimum division accuracy of about 30cm (thickness of one human body) to ensure that different human bodies can be distinguished.
S4: and comparing each human body contour map of the picture with the layered images of the radar 3D oscillogram in sequence to determine the layer where each human body is located.
In the comparison process, the position of the human body contour map in the shot picture is combined, searching and matching are carried out in the corresponding area of the radar graph, and the accuracy is improved.
S5: and determining the distance between each human body and the camera according to the layered matching result of each human body contour map on the radar 3D oscillogram.
S6: and selecting the closest human body image, intercepting the human face picture to perform human face recognition, and performing payment operation.
As can be seen from the above description, the embodiment of the present invention provides a method for recognizing a face in a multi-person scene, where a radar scanning device is configured on a camera or other shooting devices to generate a stereoscopic layer layered according to distance, and then the stereoscopic layer is compared with a shape of a person recognized and separated from a picture to calculate distances between different persons in the picture and the camera, and then the person closest to the distance is selected to intercept the face picture, which is used as an object target for face recognition. The invention comprehensively utilizes the spatial distance difference of the client, accurately positions and captures, and solves the problems that the positioning cannot be carried out or the capturing is wrong in a multi-person scene, and the traditional face screening mode only considers the face area of the photo, so that the positioning failure or the capturing error is easy to occur because the face of the client is small and the interference of the face of the person is large.
Based on the same inventive concept, the embodiment of the present application further provides a face recognition apparatus in a multi-person scene, which can be used to implement the method described in the above embodiment, as described in the following embodiments. Because the principle of solving the problem of the face recognition device in the multi-person scene is similar to that of the face recognition method in the multi-person scene, the implementation of the face recognition device in the multi-person scene can be realized by the face recognition method in the multi-person scene, and repeated parts are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
The embodiment of the present invention provides a specific implementation manner of a face recognition device in a multi-person scene, which is capable of implementing a face recognition method in a multi-person scene, and referring to fig. 6, the face recognition device in the multi-person scene specifically includes the following contents:
the photo recognition unit 10 is used for carrying out image recognition on the pre-generated multi-person photo so as to separate a plurality of human body pictures;
a picture scanning unit 20 for scanning a subject to generate a 3D oscillogram;
and the oscillogram layering unit 30 is used for layering the 3D oscillogram according to the shooting distance and comparing the layering result with the human body pictures so as to identify the human face.
In an embodiment, referring to fig. 7, the face recognition apparatus in a multi-person scene further includes: and the photo generation unit 40 is configured to generate the multi-person photo, and the photo generation unit is specifically configured to shoot the multi-person scene to generate the multi-person photo.
In one embodiment, referring to fig. 8, the oscillogram layering unit 30 includes:
a layering module 301, configured to layer the 3D oscillogram according to a preset distance unit to generate layered images with different shooting distances;
a comparison module 302, configured to compare the multiple human body pictures with the layered image to determine a layer in which each of the multiple persons is located in the layered image;
a distance determining module 303, configured to determine a shooting distance of each shot object according to a layer in which each shot object is located in the layered image;
and the face recognition module 304 is configured to perform face recognition according to the shooting distance.
In an embodiment, the human body picture includes a human body outline and a human face, referring to fig. 9, the comparing module 302 includes:
a position determining module 3021, configured to determine positions of human body contours in the human body pictures;
a comparing module 3022, configured to compare the plurality of human body pictures with the layered image according to the position.
As can be seen from the above description, in the face recognition apparatus in a multi-person scene provided in the embodiments of the present invention, radar scanning devices are configured on cameras or other shooting devices to generate stereoscopic layers layered according to distances, and then the stereoscopic layers are compared with the shapes of the persons recognized and separated from the photos to calculate the distances between different persons in the photos and the cameras, and then the person closest to the distance is selected to intercept the face photos of the persons to serve as the target object for face recognition. The invention comprehensively utilizes the spatial distance difference of the client, accurately positions and captures, and solves the problems that the positioning cannot be carried out or the capturing is wrong in a multi-person scene, and the traditional face screening mode only considers the face area of the photo, so that the positioning failure or the capturing error is easy to occur because the face of the client is small and the interference of the face of the person is large.
An embodiment of the present application further provides a specific implementation manner of an electronic device, which is capable of implementing all steps in the face recognition method in a multi-person scene in the foregoing embodiment, and referring to fig. 10, the electronic device specifically includes the following contents:
a processor (processor)1201, a memory (memory)1202, a communication interface 1203, and a bus 1204;
the processor 1201, the memory 1202 and the communication interface 1203 complete communication with each other through the bus 1204; the communication interface 1203 is configured to implement information transmission between related devices, such as a server-side device, a shooting device, a scanning device, and a client device.
The processor 1201 is configured to call the computer program in the memory 1202, and the processor executes the computer program to implement all the steps in the face recognition method in the multi-person scenario in the above embodiments, for example, the processor executes the computer program to implement the following steps:
step 100: and carrying out pattern recognition on the pre-generated multi-person picture so as to separate a plurality of human body pictures.
Step 200: the subject is scanned to generate a 3D waveform map.
Step 300: and layering the 3D oscillogram according to the shooting distance, and comparing a layering result with the plurality of human body pictures to identify the human face.
As can be seen from the above description, in the electronic device in the embodiment of the present application, the radar scanning device is configured on the camera or other shooting devices, so as to generate the stereoscopic layer layered according to the distance, compare the stereoscopic layer with the shape of the human body identified and separated from the picture, calculate the distances between different people in the picture and the camera, and then select the human body with the closest distance to intercept the facial picture of the human body, so as to serve as the target for face identification. The invention comprehensively utilizes the spatial distance difference of the client, accurately positions and captures, and solves the problems that the positioning cannot be carried out or the capturing is wrong in a multi-person scene, and the traditional face screening mode only considers the face area of the photo, so that the positioning failure or the capturing error is easy to occur because the face of the client is small and the interference of the face of the person is large.
An embodiment of the present application further provides a computer-readable storage medium capable of implementing all the steps of the face recognition method in the multi-person scenario in the foregoing embodiment, where the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, implements all the steps of the face recognition method in the multi-person scenario in the foregoing embodiment, for example, when the processor executes the computer program, the processor implements the following steps:
step 100: and carrying out pattern recognition on the pre-generated multi-person picture so as to separate a plurality of human body pictures.
Step 200: the subject is scanned to generate a 3D waveform map.
Step 300: and layering the 3D oscillogram according to the shooting distance, and comparing a layering result with the plurality of human body pictures to identify the human face.
As can be seen from the above description, in the computer-readable storage medium in the embodiment of the present application, radar scanning equipment is configured on a camera or other shooting devices to generate a stereoscopic layer layered according to distance, and then the stereoscopic layer is compared with the shape of a person identified and separated from a photo to calculate the distance between different people in the photo and the camera, and then the person closest to the human body is selected to intercept the face photo thereof as a target for face identification. The invention comprehensively utilizes the spatial distance difference of the client, accurately positions and captures, and solves the problems that the positioning cannot be carried out or the capturing is wrong in a multi-person scene, and the traditional face screening mode only considers the face area of the photo, so that the positioning failure or the capturing error is easy to occur because the face of the client is small and the interference of the face of the person is large.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (11)
1. A face recognition method under a multi-person scene is characterized by comprising the following steps:
carrying out pattern recognition on the pre-generated multi-person picture to separate out a plurality of human body pictures;
scanning a shot object to generate a 3D oscillogram;
and layering the 3D oscillogram according to the shooting distance, and comparing a layering result with the plurality of human body pictures to identify the human face.
2. The face recognition method of claim 1, wherein the step of generating the photos of the plurality of persons comprises:
and shooting the multi-person scene to generate a multi-person picture.
3. The method of claim 1, wherein the layering the 3D oscillogram according to the shooting distance and comparing the layering result with the plurality of human body pictures to identify the human face comprises:
layering the 3D oscillogram according to a preset distance unit to generate layered images with different shooting distances;
comparing the plurality of human body pictures with the layered image to determine a layer of each photographed person in the plurality of persons in the layered image;
determining the shooting distance of each shot person according to the layer of each shot person in the layered image;
and carrying out face recognition according to the shooting distance.
4. The method of claim 3, wherein the human body pictures comprise human body contours and human faces, and the comparing the plurality of human body pictures with the layered images comprises:
determining the positions of the human body outlines in the human body pictures;
and comparing the human body pictures with the layered images according to the positions.
5. The face recognition method of claim 1, wherein the manner of scanning the subject comprises: radar, sonar, laser, and infrared scanning.
6. A face recognition device under a multi-person scene, comprising:
the photo recognition unit is used for carrying out image recognition on the pre-generated multi-person photo so as to separate a plurality of human body pictures;
the picture scanning unit is used for scanning the shot person to generate a 3D oscillogram;
and the oscillogram layering unit is used for layering the 3D oscillogram according to the shooting distance and comparing the layering result with the human body pictures so as to identify the human face.
7. The face recognition apparatus of claim 6, further comprising: the photo generation unit is used for generating the multi-person photo, and the photo generation unit is specifically used for shooting the multi-person scene so as to generate the multi-person photo.
8. The face recognition apparatus of claim 6, wherein the oscillogram layering unit comprises:
the layering module is used for layering the 3D oscillogram according to a preset distance unit so as to generate layered images with different shooting distances;
the comparison module is used for comparing the human body pictures with the layered images so as to determine the layer of each photographed person in the layered images;
the distance determining module is used for determining the shooting distance of each shot person according to the layer of each shot person in the layered image;
and the face recognition module is used for carrying out face recognition according to the shooting distance.
9. The face recognition apparatus of claim 8, wherein the human body picture comprises a human body contour and a human face, and the comparison module comprises:
the position determining module is used for determining the positions of the human body outlines in the human body pictures;
and the comparison module is used for comparing the human body pictures with the layered images according to the positions.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method for face recognition in a multi-person scenario as claimed in any one of claims 1 to 5.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for face recognition in a multi-person scenario as claimed in any one of the claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010046859.1A CN111310567B (en) | 2020-01-16 | 2020-01-16 | Face recognition method and device in multi-person scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010046859.1A CN111310567B (en) | 2020-01-16 | 2020-01-16 | Face recognition method and device in multi-person scene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111310567A true CN111310567A (en) | 2020-06-19 |
| CN111310567B CN111310567B (en) | 2023-06-23 |
Family
ID=71156335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010046859.1A Active CN111310567B (en) | 2020-01-16 | 2020-01-16 | Face recognition method and device in multi-person scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111310567B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016474A (en) * | 2020-08-31 | 2020-12-01 | 重庆紫光华山智安科技有限公司 | Face recognition method, device and equipment and computer readable storage medium |
| CN113362540A (en) * | 2021-06-11 | 2021-09-07 | 江苏苏云信息科技有限公司 | Traffic ticket business processing device, system and method based on multimode interaction |
| CN113850165A (en) * | 2021-09-13 | 2021-12-28 | 支付宝(杭州)信息技术有限公司 | Face recognition method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009124644A (en) * | 2007-11-19 | 2009-06-04 | Sanyo Electric Co Ltd | Image processing device, imaging device, and image reproduction device |
| CN102567721A (en) * | 2012-01-10 | 2012-07-11 | 北京水晶石数字科技股份有限公司 | Method for detecting end positions of multiple bodies |
| JP2014086775A (en) * | 2012-10-19 | 2014-05-12 | Nippon Telegr & Teleph Corp <Ntt> | Video communication system and video communication method |
| CN104732210A (en) * | 2015-03-17 | 2015-06-24 | 深圳超多维光电子有限公司 | Target human face tracking method and electronic equipment |
| CN105578026A (en) * | 2015-07-10 | 2016-05-11 | 宇龙计算机通信科技(深圳)有限公司 | Photographing method and user terminal |
| CN106446788A (en) * | 2016-08-31 | 2017-02-22 | 山东恒宇电子有限公司 | Method for passenger flow statistic by means of high-dynamic range image based on optic nerve mechanism |
| CN106709477A (en) * | 2017-02-23 | 2017-05-24 | 哈尔滨工业大学深圳研究生院 | Face recognition method and system based on adaptive score fusion and deep learning |
| CN109344690A (en) * | 2018-08-09 | 2019-02-15 | 上海青识智能科技有限公司 | A kind of demographic method based on depth camera |
-
2020
- 2020-01-16 CN CN202010046859.1A patent/CN111310567B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009124644A (en) * | 2007-11-19 | 2009-06-04 | Sanyo Electric Co Ltd | Image processing device, imaging device, and image reproduction device |
| CN102567721A (en) * | 2012-01-10 | 2012-07-11 | 北京水晶石数字科技股份有限公司 | Method for detecting end positions of multiple bodies |
| JP2014086775A (en) * | 2012-10-19 | 2014-05-12 | Nippon Telegr & Teleph Corp <Ntt> | Video communication system and video communication method |
| CN104732210A (en) * | 2015-03-17 | 2015-06-24 | 深圳超多维光电子有限公司 | Target human face tracking method and electronic equipment |
| CN105578026A (en) * | 2015-07-10 | 2016-05-11 | 宇龙计算机通信科技(深圳)有限公司 | Photographing method and user terminal |
| CN106446788A (en) * | 2016-08-31 | 2017-02-22 | 山东恒宇电子有限公司 | Method for passenger flow statistic by means of high-dynamic range image based on optic nerve mechanism |
| CN106709477A (en) * | 2017-02-23 | 2017-05-24 | 哈尔滨工业大学深圳研究生院 | Face recognition method and system based on adaptive score fusion and deep learning |
| CN109344690A (en) * | 2018-08-09 | 2019-02-15 | 上海青识智能科技有限公司 | A kind of demographic method based on depth camera |
Non-Patent Citations (3)
| Title |
|---|
| 杨林: "基于Kinect的人体目标检测与跟踪" * |
| 王凤艳: "基于多模态输入的手势识别算法研究" * |
| 赵静: "基于TOF的运动目标检测与跟踪" * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016474A (en) * | 2020-08-31 | 2020-12-01 | 重庆紫光华山智安科技有限公司 | Face recognition method, device and equipment and computer readable storage medium |
| CN112016474B (en) * | 2020-08-31 | 2021-11-09 | 重庆紫光华山智安科技有限公司 | Face recognition method, device and equipment and computer readable storage medium |
| CN113362540A (en) * | 2021-06-11 | 2021-09-07 | 江苏苏云信息科技有限公司 | Traffic ticket business processing device, system and method based on multimode interaction |
| CN113850165A (en) * | 2021-09-13 | 2021-12-28 | 支付宝(杭州)信息技术有限公司 | Face recognition method and device |
| CN113850165B (en) * | 2021-09-13 | 2024-07-19 | 支付宝(杭州)信息技术有限公司 | Face recognition method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111310567B (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6844038B2 (en) | Biological detection methods and devices, electronic devices and storage media | |
| US10540806B2 (en) | Systems and methods for depth-assisted perspective distortion correction | |
| CN109711243B (en) | Static three-dimensional face in-vivo detection method based on deep learning | |
| CN110765923A (en) | Face living body detection method, device, equipment and storage medium | |
| CN111310567B (en) | Face recognition method and device in multi-person scene | |
| CN108549867A (en) | Image processing method, device, computer readable storage medium and electronic equipment | |
| WO2011142495A1 (en) | Apparatus and method for iris recognition using multiple iris templates | |
| KR101510312B1 (en) | 3D face-modeling device, system and method using Multiple cameras | |
| CN110956114A (en) | Face living body detection method, device, detection system and storage medium | |
| CN111444744A (en) | Living body detection method, living body detection device, and storage medium | |
| KR20090115739A (en) | Information extracting method, information extracting device, program, registering device and collating device | |
| AU2020203790B2 (en) | Transformed multi-source content aware fill | |
| CN113205057A (en) | Face living body detection method, device, equipment and storage medium | |
| JP7479729B2 (en) | Three-dimensional representation method and device | |
| JP2017123087A (en) | Program, device and method for calculating normal vector of planar object reflected in continuous photographic images | |
| CN113538315B (en) | Image processing method and device | |
| CN116051736A (en) | Three-dimensional reconstruction method, device, edge equipment and storage medium | |
| KR101715781B1 (en) | Object recognition system and method the same | |
| CN106997366B (en) | Database construction method, augmented reality fusion tracking method and terminal equipment | |
| CN106991376A (en) | With reference to the side face verification method and device and electronic installation of depth information | |
| CN110557556A (en) | Multi-object shooting method and device | |
| CN114898447B (en) | Personalized fixation point detection method and device based on self-attention mechanism | |
| CN113225484B (en) | Method and device for rapidly acquiring high-definition picture shielding non-target foreground | |
| CN115623313A (en) | Image processing method, image processing apparatus, electronic device, and storage medium | |
| CN115830354A (en) | Binocular stereo matching method, device and 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220906 Address after: 25 Financial Street, Xicheng District, Beijing 100033 Applicant after: CHINA CONSTRUCTION BANK Corp. Address before: 25 Financial Street, Xicheng District, Beijing 100033 Applicant before: CHINA CONSTRUCTION BANK Corp. Applicant before: Jianxin Financial Science and Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |