CN109948456B - Face recognition method and device applied to digital court - Google Patents
Face recognition method and device applied to digital court Download PDFInfo
- Publication number
- CN109948456B CN109948456B CN201910141298.0A CN201910141298A CN109948456B CN 109948456 B CN109948456 B CN 109948456B CN 201910141298 A CN201910141298 A CN 201910141298A CN 109948456 B CN109948456 B CN 109948456B
- Authority
- CN
- China
- Prior art keywords
- picture
- excitation
- area
- face recognition
- judge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention discloses a face recognition method and a face recognition device applied to a digital court, wherein the method comprises the following steps: acquiring a plurality of frames of court trial synthetic pictures; respectively extracting an excitation area, a judge area, an announced area and an original announcement area in each court trial synthesized picture as an excitation picture, a judge picture, an announced picture and an original announcement picture; respectively comparing the excitation picture with the judge picture, the announced picture and the original announcement picture, and judging the role on the excitation picture; and carrying out face recognition on the characters on the excitation picture by using a face recognition system. The invention can accurately judge the identity information of the role on the picture by utilizing the face recognition system to carry out face recognition on the role on the excitation picture.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a face recognition method and device applied to a digital court.
Background
In the court trial process of the digital court, there are the participation of characters such as a judge, a bookmarker, an original notice, a defendant and a witness, in order to record that each character participates in the whole court trial process in the court trial process, detect whether each court trial character meets the court trial specification, generally, the image of the close-up picture of each character is collected and displayed in a composite picture (wherein, the mode of the composite picture comprises a 2 composite mode, a 4 composite mode, a 6 composite mode and the like, for example, the television picture of the 6 composite mode can refer to the attached figure 3). In this process, in order to make the bystander clearly see the speaker who is speaking, the speeches of the speakers at different positions in the scene are generally collected, a close-up picture of the speaker is automatically tracked, and the close-up picture is displayed in the excitation picture with the largest picture and the highest resolution. In order to ensure the successful court trial, it is necessary to confirm the identity information of the roles on each of the divided sub-pictures in the composite picture.
In the prior art, a face recognition system is used for carrying out face recognition on a television composite picture of a certain frame so as to confirm identity information of roles on each separation sub-picture. The face recognition technology used by the face recognition system is performed by using a convolutional neural network, which is common in the art.
The inventor finds that the prior art has at least the following problems:
in the synthesized picture, except for the excitation picture, the occupied area of other pictures is small, the resolution of the extracted picture of the character is low, and the identity information of the character on the picture cannot be accurately judged.
Disclosure of Invention
The embodiment of the invention provides a face recognition method applied to a digital court, which is used for accurately judging the identity information of a role on a picture, and comprises the following steps:
acquiring a plurality of frames of court trial synthetic pictures;
respectively extracting an excitation area, a judge area, an announced area and an original announcement area in each court trial synthesized picture as an excitation picture, a judge picture, an announced picture and an original announcement picture;
respectively comparing the excitation picture with the judge picture, the announced picture and the original announcement picture, and judging the role on the excitation picture;
and carrying out face recognition on the characters on the excitation picture by using a face recognition system.
Optionally, the method further includes:
and detecting the judge picture, the defended picture and the original picture once every preset time, and judging whether the judge picture, the defended picture and the original picture have the object images.
Optionally, the method further includes:
respectively carrying out synthetic picture mode analysis on the obtained multi-frame court trial synthetic pictures;
and respectively extracting the excitation area, the judge area, the defended area and the original area in each frame of court trial synthesized picture into an excitation picture, a judge picture, a defended picture and an original picture according to the analysis result.
Optionally, the method further includes:
and extracting the hearing area in each court trial synthesized picture as a hearing picture, and carrying out face recognition on the role on the hearing picture by using a face recognition system.
The embodiment of the invention also provides a face recognition device applied to a digital court, which is used for accurately judging the identity information of the role on the picture, and the device comprises:
the picture acquisition module is used for acquiring a plurality of frames of court trial synthetic pictures;
the image extraction module is used for respectively extracting the excitation area, the judge area, the notice area and the original notice area in each frame of court trial synthesized picture into an excitation image, a judge image, a notice image and an original notice image;
the role judging module is used for comparing the excitation picture with the judge picture, the announced picture and the original announcement picture respectively and judging roles on the excitation picture;
and the first face recognition module is used for carrying out face recognition on the roles on the excitation picture by using the face recognition system.
Optionally, the apparatus further comprises:
and the detection module is used for detecting the judge picture, the reported picture and the original picture once every preset time interval and judging whether the judge picture, the reported picture and the original picture have the object image.
Optionally, the apparatus further comprises:
the synthetic picture mode analysis module is used for respectively carrying out synthetic picture mode analysis on the acquired multi-frame court trial synthetic pictures;
and respectively extracting the excitation area, the judge area, the defended area and the original area in each frame of court trial synthesized picture into an excitation picture, a judge picture, a defended picture and an original picture according to the analysis result.
Optionally, the apparatus further comprises:
and the second face recognition module is used for extracting the hearing area in each frame of court trial synthesized picture as a hearing picture and performing face recognition on the role on the hearing picture by using the face recognition system.
The embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program for executing the above method is stored.
In the embodiment of the invention, a plurality of court trial synthetic pictures are obtained, the excitation area, the judge area, the defended area and the original area in each court trial synthetic picture are respectively extracted as the excitation picture, the judge picture, the defended picture and the original picture, the excitation picture is respectively compared with the judge picture, the defended picture and the original picture, the role on the excitation picture is judged, and a plurality of different roles can be respectively displayed in the excitation pictures on a plurality of synthetic pictures so as to be convenient for carrying out face recognition on each role subsequently. Because the excitation picture has the largest ratio in the synthesized picture and the highest resolution, the identity information of the role on the picture can be accurately judged by utilizing the face recognition system to carry out face recognition on the role on the excitation picture.
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 described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a schematic flow chart of a face recognition method applied to a digital court in an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a face recognition apparatus applied to a digital court in an embodiment of the present invention;
FIG. 3 is a diagram illustrating an example of a TV screen in the prior art;
FIG. 4 is a diagram illustrating an exemplary process of analyzing a synthesized frame pattern according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a convolutional neural network used in the face recognition system in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
In the court trial process of the digital court, there are roles such as a judge, a bookmarker, an original notice, a defender, and a witness, in order to show the court trial pictures to the auditorium, the image of the close-up picture of each character is generally collected, and the synthesized pictures are shown to the auditorium through a television (wherein the modes of the synthesized pictures include a 2 synthesis mode, a 4 synthesis mode, a 6 synthesis mode, and the like, for example, the 6 synthesized television picture can be shown in fig. 3). In this process, in order to make the bystander clearly see the speaker who is speaking, the speeches of the speakers at different positions in the scene are generally collected, a close-up picture of the speaker is automatically tracked, and the close-up picture is displayed in the excitation picture with the largest picture and the highest resolution. In order to ensure the successful court trial, it is necessary to confirm the identity information of the roles on each of the divided sub-pictures in the composite picture.
In the prior art, a face recognition system is used for carrying out face recognition on a television composite picture of a certain frame so as to confirm identity information of roles on each separation sub-picture.
The face recognition technology used by the face recognition system is performed by using a convolutional neural network, which is common in the art. Specifically, for example, the face recognition processing flow based on the convolutional neural network is divided into four modules: face region detection module: the method is used for detecting whether the picture has a human face. And if the human face exists, determining the position of the human face in the picture and a corresponding rectangular area. The input of the convolutional neural network is a picture, and the output of the convolutional neural network is the number of the human faces in the picture and the corresponding region position of each human face in the picture.
A face calibration module: the method is used for detecting human face characteristics (eyes, eyebrows, nose, mouth and the like) in a designated area of a picture, storing the human face in the picture area as a single human face picture according to the characteristics, and performing calibration operation on the single human face picture. The input of the convolutional neural network is the output of the face region detection module and the detected picture, and the output is a single face picture after calibration.
The face feature extraction module: for extracting the feature value of each face. The input of the convolutional neural network is a single face picture, and the output is a characteristic value of each face.
Face feature comparison module: and the face characteristic value extraction module is used for comparing and calculating the face characteristic value extracted by the face characteristic extraction module with the face characteristic value in the face database to find out the identity information corresponding to the face.
In the synthesized picture, except for the excitation picture, the occupied area of other pictures is small, the resolution of the extracted picture of the character is low, and the identity information of the character on the picture cannot be accurately judged.
In order to solve the above problem, an embodiment of the present invention provides a face recognition method applied to a digital court, as shown in fig. 1, the method includes:
And 102, respectively extracting an excitation area, a judge area, an announced area and an original area in each court trial synthesis picture into an excitation picture, a judge picture, an announced picture and an original picture.
And 103, comparing the excitation picture with the judge picture, the announced picture and the original announcement picture respectively, and judging the role on the excitation picture.
And 104, carrying out face recognition on the roles on the excitation picture by using a face recognition system.
The face recognition method applied to the digital court provided by the embodiment of the invention extracts the excitation area, the judge area, the notice area and the original notice area in each court trial synthesized picture into the excitation picture, the judge picture, the notice picture and the original notice picture respectively by obtaining a plurality of court trial synthesized pictures, compares the excitation picture with the judge picture, the notice picture and the original notice picture respectively, judges the role on the excitation picture, and can enable a plurality of different roles to be displayed in the excitation pictures on a plurality of synthesized pictures respectively so as to carry out face recognition on each role subsequently. Because the excitation picture has the largest ratio in the synthesized picture and the highest resolution, the identity information of the role on the picture can be accurately judged by utilizing the face recognition system to carry out face recognition on the role on the excitation picture.
In order to judge whether a person leaves the court in the court trial process, the method further comprises the following steps:
and detecting the judge picture, the defended picture and the original picture once every preset time, and judging whether the judge picture, the defended picture and the original picture have the object images.
Specifically, the judge picture, the defendant picture and the original picture are detected once every preset time, if the judge picture, the defendant picture and the original picture have the figure images, it can be determined that the judge, the defendant and the original have no absence, and if the judge picture, the defendant picture and the original picture are blank, it can be determined that the judge, the defendant and the original have the absence.
In order to facilitate subsequent role region determination and picture extraction, the method further comprises the following steps:
respectively carrying out synthetic picture mode analysis on the obtained multi-frame court trial synthetic pictures;
and respectively extracting the excitation area, the judge area, the defended area and the original area in each frame of court trial synthesized picture into an excitation picture, a judge picture, a defended picture and an original picture according to the analysis result.
Specifically, the synthetic picture pattern analysis flow is as follows:
a. it is detected whether the synthesis mode is 6. If yes, entering step e, if not, entering step b;
b. whether the detection is the 4-synthesis mode is detected. If yes, entering step e, if not, entering step c;
c. it is detected whether 2 synthesis mode is present. If yes, entering step e, if not, entering step d;
d. if the composite picture is detected to be neither the 6 composite mode, the 4 composite mode or the 2 composite mode, the composite picture is a single picture, and the step e is entered;
e. and completing the detection of the synthesis mode of the court trial synthesis picture, and entering the next process for processing.
Referring to fig. 4, according to the 6 synthesis mode, an excitation frame region and other 5 frame regions are obtained;
comparing the excitation picture area with other 5 picture areas, judging whether the excitation picture area is the same as one of the other 5 picture areas (whether the excitation picture area is the same role), if so, entering the next process, and if not, obtaining the excitation picture area and other 3 picture areas according to a 4-synthesis mode;
comparing the excitation picture area with the other 3 picture areas, judging whether the excitation picture area is the same as one of the other 3 picture areas (whether the excitation picture area is the same role), if so, entering the next process, and if not, obtaining the excitation picture area and the other 1 picture areas according to the 2-synthesis mode;
comparing the excitation picture area with other 1 picture areas, judging whether the excitation picture area is the same as the other 1 picture areas (whether the excitation picture area is the same role), if so, entering the next process, and if not, the picture is in a single picture mode.
In an embodiment of the present invention, in order to determine whether the hearing people come in or go out of the court site during the court trial, the method further includes:
and extracting the hearing area in each court trial synthesized picture as a hearing picture, and carrying out face recognition on the role on the hearing picture by using a face recognition system.
Based on the same inventive concept, the embodiment of the present invention further provides a face recognition apparatus applied to a digital court, as described in the following embodiments. Because the principle of solving the problems of the face recognition device applied to the digital court is similar to the face recognition method applied to the digital court, the implementation of the face recognition device applied to the digital court can refer to the implementation of the face recognition method applied to the digital court, and repeated parts are not described again. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
An embodiment of the present invention further provides a face recognition apparatus applied to a digital court, as shown in fig. 2, including:
the image acquisition module 201 is used for acquiring a plurality of frames of court trial synthetic images;
the picture extraction module 202 is configured to extract an excitation region, a judge region, an announced region and an original region in each court trial composite picture as an excitation picture, a judge picture, an announced picture and an original picture respectively;
the role judging module 203 is used for comparing the excitation picture with the judge picture, the announced picture and the original picture respectively and judging roles on the excitation picture;
and the first face recognition module 204 is configured to perform face recognition on the role on the excitation picture by using a face recognition system.
In an embodiment of the present invention, the apparatus further includes:
and the detection module is used for detecting the judge picture, the reported picture and the original picture once every preset time interval and judging whether the judge picture, the reported picture and the original picture have the object image.
In an embodiment of the present invention, the apparatus further includes:
the synthetic picture mode analysis module is used for respectively carrying out synthetic picture mode analysis on the acquired multi-frame court trial synthetic pictures;
and respectively extracting the excitation area, the judge area, the defended area and the original area in each frame of court trial synthesized picture into an excitation picture, a judge picture, a defended picture and an original picture according to the analysis result.
In an embodiment of the present invention, the apparatus further includes:
and the second face recognition module is used for extracting the hearing area in each frame of court trial synthesized picture as a hearing picture and performing face recognition on the role on the hearing picture by using the face recognition system.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the method when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, and the computer readable storage medium stores a computer program for executing the method.
In the detection of the synthetic mode of the court trial synthetic picture and the detection of the role of the excitation picture, the comparison of two pictures is involved, and whether the two pictures are collected by the same camera or not, namely whether the two pictures are the same role or not, is compared.
In the invention, a Convolutional neural network is used to complete the comparison of two pictures, a Caffe (conventional deep learning framework) is used to create the Convolutional neural network, and the input of the Convolutional neural network is two gray pictures, so that before entering the Convolutional network, the RGB pictures need to be converted into the gray pictures and then sent into the Convolutional neural network. The structure of the convolutional neural network can be seen in fig. 5. The method comprises the following specific steps:
the convolutional neural network has 2 input layers (input _ layer) corresponding to two gray pictures. The resolution of the two gray level pictures is 256x256, and the channel (channel) is 1;
the outputs of the 2 input layers are to the fusion layer (Concat _ layer). Concat layer fuses the two grayscale images into one image. The resolution of the fused image is 256x256, and the channel (channel) is 2;
the Concat _ layer outputs (channel 2, resolution 256x256 image) to the Convolume _ layer2, which performs a Convolution operation. Convolution parameters: 96 convolution kernels, each convolution kernel size (7x7), each convolution kernel step size (3x 3);
the Convolation _ layer2 layer outputs to the ReLU _ layer3 to execute the operation of the activation function, and introduces the nonlinear characteristic in the network;
the ReLU _ layer3 layer is output to the Pooling _ layer4 to perform the Pooling operation. The pooling parameter is as follows: pooled kernel size (2x2), pooled step size (2x 2);
the Pooling _ layer4 layer is output to the Convolition _ layer5, which performs a Convolution operation. Convolution parameters: 192 convolution kernels, each convolution kernel size (5x5), each convolution kernel step size (1x 1);
the Convolation _ layer5 layer outputs to the ReLU _ layer6 to execute the operation of the activation function, and introduces the nonlinear characteristic in the network;
the ReLU _ layer6 layer is output to the Pooling _ layer7 to perform the Pooling operation. The pooling parameter is as follows: pooled kernel size (2x2), pooled step size (2x 2);
the Pooling _ layer7 layer is output to the Convolition _ layer8, which performs a Convolution operation. Convolution parameters: 256 convolution kernels, each convolution kernel size (3x3), each convolution kernel step size (1x 1);
the Convolation _ layer8 layer outputs to the ReLU _ layer9 to execute the operation of the activation function, and introduces the nonlinear characteristic in the network;
the ReLU _ layer9 layer outputs to the Flatten _ layer10, and the multidimensional tensor output by the ReLU _ layer9 is converted into a 1-bit tensor, namely a vector;
the Flatten _ layer10 layer outputs to InnerProduct _ layer10, which performs the inner product operation. Outputting a 2048-dimensional vector;
the InnerProduct _ layer10 layer outputs to InnerProduct _ layer12, which performs the inner product operation. Outputting a 1024-dimensional vector;
the InnerProduct _ layer12 is output to the Sigmoid _ layer12, and the result is output. When the output of the Sigmoid _ layer12 layer is yes, the two images are not in the same role; when the Sigmoid _ layer12 layer output is 1, it indicates that the two images are of the same role.
The method adopts a random gradient descent mode to carry out convolutional neural network learning, the cost function adopts a cross entropy cost function, the learning rate (learning rate) is 1.0, the momentum (momentum) is 0.9, and the weight attenuation is 0.0005.
In the embodiment of the invention, a plurality of court trial synthetic pictures are obtained, the excitation area, the judge area, the defended area and the original area in each court trial synthetic picture are respectively extracted as the excitation picture, the judge picture, the defended picture and the original picture, the excitation picture is respectively compared with the judge picture, the defended picture and the original picture, the role on the excitation picture is judged, and a plurality of different roles can be respectively displayed in the excitation pictures on a plurality of synthetic pictures so as to be convenient for carrying out face recognition on each role subsequently. Because the excitation picture has the largest ratio in the synthesized picture and the highest resolution, the identity information of the role on the picture can be accurately judged by utilizing the face recognition system to carry out face recognition on the role on the excitation picture.
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 above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A face recognition method applied to a digital court is characterized by comprising the following steps:
acquiring a plurality of frames of court trial synthetic pictures;
respectively extracting an excitation area, a judge area, a notice area and an original notice area in each court trial synthesized picture as an excitation picture, a judge picture, a notice picture and an original notice picture, wherein the excitation picture is the picture with the largest proportion and the highest resolution in the synthesized picture;
respectively comparing the excitation picture with the judge picture, the announced picture and the original announcement picture, and judging the role on the excitation picture;
and carrying out face recognition on the characters on the excitation picture by using a face recognition system.
2. The method of claim 1, further comprising:
and detecting the judge picture, the defended picture and the original picture once every preset time, and judging whether the judge picture, the defended picture and the original picture have the object images.
3. The method of claim 1, further comprising:
respectively carrying out synthetic picture mode analysis on the obtained multi-frame court trial synthetic pictures;
and respectively extracting the excitation area, the judge area, the defended area and the original area in each frame of court trial synthesized picture into an excitation picture, a judge picture, a defended picture and an original picture according to the analysis result.
4. The method of claim 1, further comprising:
and extracting the hearing area in each court trial synthesized picture as a hearing picture, and carrying out face recognition on the role on the hearing picture by using a face recognition system.
5. A face recognition apparatus for use in a digital court, comprising:
the picture acquisition module is used for acquiring a plurality of frames of court trial synthetic pictures;
the image extraction module is used for respectively extracting an excitation area, a judge area, a notice area and an original notice area in each frame of court trial synthesized image into an excitation image, a judge image, a notice image and an original notice image, wherein the excitation image is the image with the largest proportion and the highest resolution in the synthesized image;
the role judging module is used for comparing the excitation picture with the judge picture, the announced picture and the original announcement picture respectively and judging roles on the excitation picture;
and the first face recognition module is used for carrying out face recognition on the roles on the excitation picture by using the face recognition system.
6. The apparatus of claim 5, further comprising:
and the detection module is used for detecting the judge picture, the reported picture and the original picture once every preset time interval and judging whether the judge picture, the reported picture and the original picture have the object image.
7. The apparatus of claim 5, further comprising:
the synthetic picture mode analysis module is used for respectively carrying out synthetic picture mode analysis on the acquired multi-frame court trial synthetic pictures;
and respectively extracting the excitation area, the judge area, the defended area and the original area in each frame of court trial synthesized picture into an excitation picture, a judge picture, a defended picture and an original picture according to the analysis result.
8. The apparatus of claim 5, further comprising:
and the second face recognition module is used for extracting the hearing area in each frame of court trial synthesized picture as a hearing picture and performing face recognition on the role on the hearing picture by using the face recognition system.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910141298.0A CN109948456B (en) | 2019-02-26 | 2019-02-26 | Face recognition method and device applied to digital court |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910141298.0A CN109948456B (en) | 2019-02-26 | 2019-02-26 | Face recognition method and device applied to digital court |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109948456A CN109948456A (en) | 2019-06-28 |
| CN109948456B true CN109948456B (en) | 2020-12-18 |
Family
ID=67007717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910141298.0A Active CN109948456B (en) | 2019-02-26 | 2019-02-26 | Face recognition method and device applied to digital court |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109948456B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751041A (en) * | 2015-03-03 | 2015-07-01 | 北京卓识数云科技有限公司 | Authentication method, system and mobile terminal |
| CN106231259A (en) * | 2016-07-29 | 2016-12-14 | 北京小米移动软件有限公司 | The display packing of monitored picture, video player and server |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105592268A (en) * | 2016-03-03 | 2016-05-18 | 苏州科达科技股份有限公司 | Video conferencing system, processing device and video conferencing method |
| CN106384237A (en) * | 2016-08-31 | 2017-02-08 | 北京志光伯元科技有限公司 | Member authentication-management method, device and system based on face identification |
| CN108269333A (en) * | 2018-01-08 | 2018-07-10 | 平安科技（深圳）有限公司 | Face identification method, application server and computer readable storage medium |
-
2019
- 2019-02-26 CN CN201910141298.0A patent/CN109948456B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751041A (en) * | 2015-03-03 | 2015-07-01 | 北京卓识数云科技有限公司 | Authentication method, system and mobile terminal |
| CN106231259A (en) * | 2016-07-29 | 2016-12-14 | 北京小米移动软件有限公司 | The display packing of monitored picture, video player and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109948456A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805047B (en) | Living body detection method and device, electronic equipment and computer readable medium | |
| US11830230B2 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| US11048948B2 (en) | System and method for counting objects | |
| US8577137B2 (en) | Image processing apparatus and method, and program | |
| CN108875481B (en) | Method, device, system and storage medium for pedestrian detection | |
| US8548247B2 (en) | Image processing apparatus and method, and program | |
| US11861810B2 (en) | Image dehazing method, apparatus, and device, and computer storage medium | |
| CN109740589B (en) | Asynchronous object ROI detection method and system in video mode | |
| CN111753782B (en) | False face detection method and device based on double-current network and electronic equipment | |
| CN111985281A (en) | Image generation model generation method and device and image generation method and device | |
| CN109784230A (en) | A kind of facial video image quality optimization method, system and equipment | |
| CN109145861B (en) | Emotion recognition device and method, head-mounted display equipment and storage medium | |
| Devadethan et al. | Face detection and facial feature extraction based on a fusion of knowledge based method and morphological image processing | |
| CN105979283A (en) | Video transcoding method and device | |
| CN109948456B (en) | Face recognition method and device applied to digital court | |
| US11275947B2 (en) | Image processing system, image processing method, and image processing program | |
| CN106611417A (en) | A method and device for classifying visual elements as a foreground or a background | |
| CN113221971B (en) | Multi-scale crowd counting method and system based on front and back feature fusion | |
| CN113544700A (en) | Neural network training method and device, and associated object detection method and device | |
| JP6132996B1 (en) | Image processing apparatus, image processing method, and image processing program | |
| JP2011018199A (en) | Apparatus, method and program for processing image | |
| CN116580446B (en) | Iris characteristic recognition method and system for vascular diseases | |
| WO2013034878A2 (en) | Image processing | |
| CN112465792A (en) | Human face quality evaluation method and related device | |
| CN114582013A (en) | Behavior gesture recognition method for shielded part of human body |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100094 5 floor 101, 6 building, No. 3, Fung Xiu Road, Haidian District, Beijing. Applicant after: BEIJING HUAXIA DENTSU TECHNOLOGY Co.,Ltd. Address before: 100094 5 floor 101, 6 building, No. 3, Fung Xiu Road, Haidian District, Beijing. Applicant before: BEIJING CHINASYS TECHNOLOGIES Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |