CN111401313B - Method, system and equipment for identifying and positioning physical education competition personnel - Google Patents
Method, system and equipment for identifying and positioning physical education competition personnel Download PDFInfo
- Publication number
- CN111401313B CN111401313B CN202010278330.2A CN202010278330A CN111401313B CN 111401313 B CN111401313 B CN 111401313B CN 202010278330 A CN202010278330 A CN 202010278330A CN 111401313 B CN111401313 B CN 111401313B
- Authority
- CN
- China
- Prior art keywords
- number plate
- matching
- images
- subsystem
- image
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method and a system for identifying and positioning sports contestants, wherein the system comprises a face identification subsystem, a number plate identification subsystem, an accurate matching and fuzzy matching subsystem and a global matching subsystem, wherein the face identification subsystem executes face identification based on deep learning; the number plate recognition subsystem executes number plate recognition based on deep learning, acquires images of sports events, sequentially recognizes each image, stores all number plates contained in the images in a background database through character recognition, and extracts and distributes the images correspondingly containing the number plates to users after acquiring personal numbers input by sports competition personnel; the precise matching and fuzzy matching subsystem combines the precise matching and the fuzzy matching to identify the number plate; the global matching subsystem performs matching of the face information and the number plate information of the individual based on the global.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a method, a system and equipment for identifying and positioning physical education competition personnel.
Background
The artificial intelligence has rapidly developed in the aspects of data, algorithm and computing power, and a new round of development is brought under the large background of global economic digital transformation. The influence of the artificial intelligence wave is far beyond the prior art, and the most remarkable characteristic is that the influence is diffused from the professional field to the popular field.
As one of the most common applications of artificial intelligence, which is open to the public, face recognition has been applied to security, authentication, and the like, and shows its powerful capabilities in the fields of finance, transportation, medical treatment, logistics, and the like, such as train station face authentication, paymate wechat authentication, bank financial authentication, and the like. Face recognition is becoming an indispensable part of people's lives.
For large crowd activities, such as large sports events, music festivals, etc., face recognition has been applied in face verification approaches.
With the popularity of global marathon competition, marathon officials may capture a large number of images of a competition scene and publish the corresponding images. However, when a user wishes to extract an image of a person, there is often no way to face a huge amount of images. In the prior art, user images are often extracted through face recognition, however, in an actual event, due to various reasons such as facial expression deformation caused by mutual shielding and movement of a camera and competitors, all images of a user cannot be accurately extracted through a face recognition scheme.
In a marathon race, many contestants do not have a way to acquire personal images because many event organizers do not employ efficient techniques for the distribution of event images. And a large number of images are often omitted in face recognition adopted in part of the market, so that the distribution of the event images is not ideal.
Disclosure of Invention
One of the objectives of the present invention is to provide a method, a system and a device for identifying and positioning sports contestants, which identify the number plate on the sports contestant and assist with face identification, thereby improving the accuracy of identification and making the distribution of the event images more accurate and smooth.
For at least one of the objects of the present invention, there is provided a method for identifying and positioning persons involved in sports competition, comprising the steps of:
a face recognition step;
identifying the number plate;
combining precise matching and fuzzy matching; and
a global matching step;
in the face recognition step, 68 feature point detections are executed on the faces of all contestants in the sports contestant database based on a face recognition algorithm; storing the identified detection points into a background database; acquiring personal face information of sports competition personnel, extracting matched face data in a background database, and positioning corresponding competition images;
in the number plate identification step, sports event images are obtained, each image is sequentially identified, and all number plates contained in the images are stored in a background database through character identification; after acquiring the personal number input by the sports contestant, extracting and distributing the image correspondingly containing the number plate to the user;
in the step of combining the precise matching and the fuzzy matching, all number plate information input by a user is obtained in response to a precise matching request, and corresponding images are searched out according to precise numbers and distributed to the user; responding to the fuzzy matching request, acquiring part of number plate information input by a user, searching all images containing the part of number plate information, extracting and distributing the images to the user;
in the global matching step, personal face information and input number plate information shot by the sports contestant are acquired, images including faces and images of number plates are output, and the images are returned to the user after being repeated.
In some embodiments, wherein the number plate recognizing step further comprises the steps of: the method comprises the steps of acquiring an image of a number plate area, and performing filtering processing, image enhancement processing, image marginalization sharpening processing, image texture analysis processing and morphology processing on the acquired image of the number plate area.
In some embodiments, wherein the number plate identifying step further comprises the steps of: and performing text detection on the acquired images of the number plate areas by adopting CTPN, seglink, textBoxes, FTSN, pixellink and CRAFT algorithms based on an optical character recognition technology.
According to another aspect of the present invention, there is also provided a sports contestant identification and location apparatus, comprising:
a memory for storing a software application,
and the processor is used for executing the software application program, and each program of the software application program correspondingly executes the steps in the identification and positioning method for the sports contestants.
According to another aspect of the present invention, there is also provided a sports contestant identification and positioning system, comprising a face identification subsystem, a number plate identification subsystem, an exact matching and fuzzy matching subsystem, and a global matching subsystem, wherein the face identification subsystem performs face identification based on deep learning; the number plate identification subsystem executes number plate identification based on deep learning, acquires images of sports events, sequentially identifies each image, stores all number plates contained in the images in a background database through character identification, and extracts and distributes the images correspondingly containing the number plates to users after acquiring personal numbers input by sports contestants; the accurate matching and fuzzy matching subsystem combines the accurate matching and the fuzzy matching to identify the number plate; the global matching subsystem performs matching of the face information and the number plate information of the individual based on the global.
In some embodiments, the face recognition subsystem is provided with a feature point detection module, a detection point saving module and an extraction and positioning module, the feature point detection module detects 68 feature points of faces of all contestants in the database through a face recognition algorithm, the detection point saving module saves the identified detection points in a background database, and after the contestants input personal face information, the extraction and positioning module extracts faces matched in the database, so as to position corresponding contest images.
In some embodiments, the number plate recognition subsystem acquires an image of the number plate region, and performs a filtering process, an image enhancement process, an image marginalization sharpening process, an image texture analysis process, and a morphological process on the acquired image of the number plate region.
In some embodiments, wherein the number plate recognition subsystem performs a filtering process through an image smoothing process and an image denoising process, performs an image texture analysis through a skeleton removal process and a connectivity process, and performs a morphological process through a dilation process, a dress process, and an open/close operation process; wherein the number plate recognition subsystem performs text detection on the acquired images of the number plate area using CTPN, seglink, textBoxes, FTSN, pixellink, and CRAFT algorithms in combination.
In some embodiments, the precise matching and fuzzy matching subsystem includes a precise matching module and a fuzzy matching module, the precise matching module searches out corresponding images according to precise numbers and distributes the images to users, and the fuzzy matching module is configured to: and responding to the fuzzy matching request, acquiring partial number plate information input by the user, searching all images containing the partial number plate information, and extracting and distributing the images to the user.
In some embodiments, the global matching subsystem is provided with a shooting information receiving and processing module and a duplication elimination module, the shooting information receiving and processing module receives the shot individual face information and the input number plate information, and outputs the image containing the face and the number plate after processing, and the duplication elimination module returns the individual face information and the input number plate information to the user after duplication elimination.
Drawings
FIG. 1 is a flow chart of the steps of a method for identifying and locating a sports participant according to one embodiment of the invention.
FIG. 2 is a block diagram of a sports contestant identification location system, according to one embodiment of the present invention.
Detailed Description
The following description is presented to disclose the invention so as to enable any person skilled in the art to practice the invention. The preferred embodiments described below are by way of example only, and other obvious variations will occur to those skilled in the art. The basic principles of the invention, as defined in the following description, may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.
It is understood that the terms "a" and "an" should be interpreted as meaning "at least one" or "one or more," i.e., that a quantity of one element may be one in one embodiment, while a quantity of another element may be plural in other embodiments, and the terms "a" and "an" should not be interpreted as limiting the quantity.
The present invention relates to a computer program. Fig. 1 is a flow chart of a method for identifying and positioning a sports contestant according to the present invention, which illustrates a solution for controlling or processing an external object or an internal object of a computer by executing a computer program prepared according to the above flow on the basis of a computer program processing flow to solve the problems of the present invention.
As shown in fig. 1, the method for identifying and positioning the sports contestants comprises the following steps:
a face recognition step: based on a face recognition algorithm, 68 feature point detections are executed on the faces of all contestants in the sports contestant database; storing the identified detection points into a background database; acquiring personal face information of sports competition personnel, extracting matched face data in a background database, and positioning corresponding competition images;
number plate identification: acquiring images of the sports event, sequentially identifying each image, and storing all number plates contained in the images in a background database through character identification; after the personal number input by the sports contestant is acquired, the image correspondingly containing the number plate is extracted and distributed to the user. Wherein the number plate recognizing step further comprises: acquiring an image of a number plate area, and performing filtering processing, image enhancement processing, image marginalization sharpening processing, image texture analysis processing and morphology processing on the acquired image of the number plate area; performing Text Detection on the acquired Image of the number plate Region by adopting CTPN (Detecting Text in Natural Image with connecting Text property Network), seglink (Detecting original Text in Natural Image by Linking search), textBox (A Fast Text Detector with a Single depth Network), FTSN (fused Text Segmentation Network), pixillink (Detecting Scene Text entry selection) and CRAFT (channel Region for Text Detection) algorithms based on an optical Character recognition technology;
and combining precise matching and fuzzy matching: responding to the accurate matching request, acquiring all number plate information input by the user, searching out corresponding images according to accurate numbers and distributing the images to the user; responding to the fuzzy matching request, acquiring part of number plate information input by a user, searching all images containing the part of number plate information, extracting and distributing the images to the user;
a global matching step: the method comprises the steps of obtaining personal face information and input number plate information shot by sports contestants, outputting images containing faces and images containing number plates, and returning the images to a user after duplication is removed.
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.
It will be understood by those skilled in the art that the method for identifying and locating a position of a person participating in a sports competition according to the present invention can be implemented by hardware, software, or a combination of hardware and software. The present invention can be realized in a centralized fashion in at least one computer system, or in a distributed fashion where different elements are spread across several interconnected computer systems. Any kind of computer system or other apparatus adapted for carrying out the methods described herein is suited. A typical combination of hardware and software could be a general purpose computer system with a computer program that, when being loaded and executed, controls the computer system such that it carries out the methods described herein.
The present invention can be embedded in a computer program product, which comprises all the features enabling the implementation of the methods described herein. The computer program product is embodied in one or more computer-readable storage media having computer-readable program code embodied therein. According to another aspect of the present invention, there is also provided a computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, is capable of performing the steps of the method for identifying and locating persons involved in sports competition of the present invention. Computer storage media is media in computer memory for storage of some discrete physical quantity. Computer storage media includes, but is not limited to, semiconductors, magnetic disk storage, magnetic cores, magnetic drums, magnetic tape, laser disks, and the like. It will be appreciated by persons skilled in the art that computer storage media are not limited by the foregoing examples, which are intended to be illustrative only and not limiting of the invention.
According to another aspect of the present invention, there is also provided a sports competitor identification and positioning device, comprising: a software application, a memory for storing the software application, and a processor for executing the software application. Each program of the software application program can correspondingly execute the steps in the identification and positioning method for the sports contestants.
A typical combination of hardware and software could be a general purpose computer system with a computer program that, when being loaded and executed, controls the computer system such that it carries out the method of identifying and locating persons during a sports competition as disclosed herein.
In correspondence with the embodiment of the method for identifying and positioning the sports competitors, according to another aspect of the invention, a system for identifying and positioning the sports competitors is also provided, and the system for identifying and positioning the sports competitors is an application of the method for identifying and positioning the sports competitors in the invention on the improvement of a computer program. The sports contestant identification and positioning system comprises a face identification subsystem 10, a number plate identification subsystem 20, an accurate matching and fuzzy matching subsystem 30 and a global matching subsystem 40.
The face recognition subsystem 10 performs face recognition based on deep learning. The face recognition subsystem 10 is provided with a feature point detection module 11, a detection point storage module 12 and an extraction and positioning module 13.
The feature point detection module 11 detects 68 feature points of the faces of all the contestants in the database through a face recognition algorithm in an open-source Dlib machine learning algorithm library; for the identified detection points, the detection point storage module 12 stores the identified detection points in a background database; after the match participants input the personal face information, the extracting and positioning module 13 extracts the matched faces in the database, thereby positioning the corresponding match images.
The number plate recognition subsystem 20 performs number plate recognition based on deep learning. With the rapid development of neural networks in computer vision, the accuracy of OCR (optical character recognition) is also greatly improved compared with the conventional technology. Under the large background of deep learning, character recognition is also expanded from the recognition of traditional scenes to the character recognition of general scenes, namely, the character recognition of natural scenes. The current mainstream technical solutions are basically divided into two categories, namely two-stage identification and end-to-end identification.
Two-stage divides the recognition into Two steps: text detection and character recognition. The text detection is to detect the area with characters in the scene and then provide the text box with a character recognition algorithm to recognize the characters. The number plate recognition subsystem 20 updates the algorithm model, and improves the recognition accuracy of the user.
In an actual game, problems such as a number plate inclination, a shooting blur, and an overexposure due to player movement are caused. The number plate identification subsystem 20 adopts the following image processing methods, so that the image quality of the number plate area is improved: filtering (e.g., image smoothing, image denoising), image enhancement, image marginalization sharpening, image texture analysis (e.g., skeleton removal, connectivity), morphological processing (e.g., dilation, apparel, on-off operations, etc.).
In the text detection, the algorithm in the number plate identification subsystem 20 can also solve the problems such as image inclination, image deformation and the like, so that the detection is more accurate. The number plate identification subsystem 20 uses a number of algorithmic frameworks as follows: CTPN (Detecting Text in Natural Image with connecting Text forwarding Network), seglink (Detecting organized Text in Natural Images by Linking documents), textBox (A Fast Text Detector with a Single Deep New Network), FTSN (fused Text segmentation Network), and the like.
Based on the latest word recognition algorithm research, the number plate recognition subsystem 20 provides a multi-leading edge algorithm framework: pixellink (Detecting Scene Text Instance Segmentation), CRAFT (Character Region artifact for Text Detection), and the like.
The number plate recognition subsystem 20 collects all the game images, sequentially recognizes each image, stores all the number plates included in the images in a background database through character recognition, and extracts and distributes the images correspondingly including the number plates to users after the participants input the personal numbers.
The exact match and fuzzy match subsystem 30 combines the exact match and the fuzzy match to perform the identification of the number plate. Not all number plates can be identified accurately due to the mutual shielding of the participants. The exact match and fuzzy match subsystem 30 thus provides two modes for the user to use, namely exact match and fuzzy match. The exact match and fuzzy match subsystem 30 includes an exact match module 31 and a fuzzy match module 32.
Specifically, the user inputs all number plates, and the precise matching module 31 searches out corresponding images according to precise numbers and distributes the images to the user.
Specifically, the user inputs a part of the number plate (for example, the number of the number plate is 12345, and the user inputs only 123), the fuzzy matching module 32 performs fuzzy matching on corresponding numbers, searches all images containing the numbers, and extracts and distributes the images to the user. The fuzzy matching of the fuzzy matching module 32 can effectively avoid missing blocked images, thereby improving the overall reliability of the system.
The global matching subsystem 40 performs matching of face information and number plate information of an individual based on a global basis. The global matching subsystem 40 is provided with a shooting information receiving processing module 41 and a deduplication module 42.
The sports contestant shoots individual face information and input number plate information, shoot individual face information and input number plate information that information reception processing module 41 received the shooting, and the image that the output contains the face and the image of number plate after the processing, remove and return back to the user after module 42 removes the repetition with individual face information and input number plate information. By combining the two algorithms, the efficiency and accuracy of distribution can be greatly improved.
The sports competition personnel identification and positioning system provided by the invention has the advantages that the OCR technology and the face technology are combined, the actual situation is considered, the fuzzy matching scheme is supplemented, the identification accuracy and the searching accuracy are greatly improved, the sports competition sponsor is helped to better distribute images, and the efficiency is improved.
It will be appreciated by those skilled in the art that the present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, systems and computer program products according to the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations 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 and/or block diagram block or blocks.
It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are given by way of example only and are not limiting of the invention. The objects of the invention have been fully and effectively accomplished. The functional and structural principles of the present invention have been shown and described in the embodiments, and any variations or modifications may be made to the embodiments of the present invention without departing from such principles.
Claims (3)
1. A method for identifying and positioning sports contestants is characterized by comprising the following steps of:
a face recognition step;
identifying the number plate;
combining precise matching and fuzzy matching; and
a global matching step;
in the face recognition step, 68 feature point detections are executed on the faces of all contestants in the sports contestant database based on a face recognition algorithm; storing the identified detection points into a background database; acquiring personal face information of sports competition personnel, extracting matched face data in a background database, and positioning a corresponding competition image;
in the number plate identification step, sports event images are obtained, each image is sequentially identified, and all number plates contained in the images are stored in a background database through character identification; after acquiring the personal number input by the sports contestant, extracting and distributing the image correspondingly containing the number plate to the user;
in the step of combining the precise matching and the fuzzy matching, the precise matching and the fuzzy matching are combined to identify the number plate; responding to the precise matching request, acquiring all number plate information input by the user, searching out corresponding images according to precise numbers and distributing the images to the user; responding to the fuzzy matching request, acquiring partial number plate information input by a user, searching all images containing the partial number plate information, and extracting and distributing the images to the user;
in the global matching step, personal face information and input number plate information shot by sports contestants are acquired, images including faces and images of number plates are output, and the images are returned to users after being subjected to repetition;
wherein the number plate recognizing step further comprises the steps of: acquiring an image of a number plate area, and performing image smoothing, filtering processing of image noise reduction, image enhancement processing, image edge sharpening processing, image texture analysis processing of skeleton removal and connectivity and morphological processing of expansion, corrosion and opening and closing operations on the acquired image of the number plate area;
wherein the number plate recognizing step further comprises the steps of: performing number plate recognition based on deep learning; updating the algorithm model, and improving the identification precision of the user; and performing text detection on the acquired images of the number plate areas by adopting CTPN, seglink, textBoxes, FTSN, pixellink and CRAFT algorithms based on an optical character recognition technology.
2. A sports contestant identification and positioning apparatus, comprising:
a memory for storing a software application,
a processor for executing said software applications, each of said software applications correspondingly performing the steps in the sports contestant identification and location method as recited in claim 1.
3. A sports competition personnel identification and positioning system is characterized by comprising a face identification subsystem, a number plate identification subsystem, an accurate matching and fuzzy matching subsystem and a global matching subsystem, wherein the face identification subsystem executes face identification based on deep learning; the number plate identification subsystem executes number plate identification based on deep learning, acquires images of sports events, sequentially identifies each image, stores all number plates contained in the images in a background database through character identification, and extracts and distributes the images correspondingly containing the number plates to users after acquiring personal numbers input by sports contestants; the accurate matching and fuzzy matching subsystem combines the accurate matching and the fuzzy matching to identify the number plate; the global matching subsystem performs matching of the face information and the number plate information of the individual based on the global; the face recognition subsystem is provided with a feature point detection module, and the feature point detection module detects 68 feature points of the faces of all contestants in the database through a face recognition algorithm; the global matching subsystem is provided with a duplication elimination module which is used for eliminating duplication of personal face information and input number plate information and returning the personal face information and the input number plate information to the user; the face recognition subsystem is provided with a detection point storage module and an extraction positioning module, the detection point storage module stores the recognized detection points in a background database, and after the participants input personal face information, the extraction positioning module extracts the faces matched in the database so as to position corresponding participating images; the number plate identification subsystem acquires an image of a number plate area, and performs filtering processing, image enhancement processing, image edge sharpening processing, image texture analysis processing and morphological processing on the acquired image of the number plate area; the number plate identification subsystem executes filtering processing through image smoothing processing and image noise reduction processing, executes image texture analysis through skeleton removing processing and connectivity processing, and executes morphological processing through expansion processing, corrosion processing and opening and closing operation processing; wherein the number plate recognition subsystem performs text detection on the acquired image of the number plate area in combination with CTPN, seglink, textBox, FTSN, pixellink, and CRAFT algorithms; the precise matching and fuzzy matching subsystem comprises a precise matching module and a fuzzy matching module, the precise matching module searches out corresponding images according to precise numbers and distributes the images to users, and the fuzzy matching module is configured to: responding to the fuzzy matching request, acquiring part of number plate information input by a user, searching all images containing the part of number plate information, extracting and distributing the images to the user; the global matching subsystem is provided with a shooting information receiving and processing module, the shooting information receiving and processing module receives the shot individual face information and the input number plate information, and outputs the image containing the face and the image containing the number plate after processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010278330.2A CN111401313B (en) | 2020-04-10 | 2020-04-10 | Method, system and equipment for identifying and positioning physical education competition personnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010278330.2A CN111401313B (en) | 2020-04-10 | 2020-04-10 | Method, system and equipment for identifying and positioning physical education competition personnel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111401313A CN111401313A (en) | 2020-07-10 |
| CN111401313B true CN111401313B (en) | 2022-10-11 |
Family
ID=71414147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010278330.2A Active CN111401313B (en) | 2020-04-10 | 2020-04-10 | Method, system and equipment for identifying and positioning physical education competition personnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401313B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966848B (en) * | 2020-07-18 | 2024-07-12 | 珠海格力电器股份有限公司 | Part visual positioning method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529520A (en) * | 2016-10-09 | 2017-03-22 | 中国传媒大学 | Marathon match associated photo management method based on athlete number identification |
| CN107609108A (en) * | 2017-09-13 | 2018-01-19 | 杭州景联文科技有限公司 | A kind of sportsman's photo method for sorting based on number slip identification and recognition of face |
| CN108573202A (en) * | 2017-03-17 | 2018-09-25 | 北京旷视科技有限公司 | Identity identifying method, device and system and terminal, server and storage medium |
-
2020
- 2020-04-10 CN CN202010278330.2A patent/CN111401313B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529520A (en) * | 2016-10-09 | 2017-03-22 | 中国传媒大学 | Marathon match associated photo management method based on athlete number identification |
| CN108573202A (en) * | 2017-03-17 | 2018-09-25 | 北京旷视科技有限公司 | Identity identifying method, device and system and terminal, server and storage medium |
| CN107609108A (en) * | 2017-09-13 | 2018-01-19 | 杭州景联文科技有限公司 | A kind of sportsman's photo method for sorting based on number slip identification and recognition of face |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111401313A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Singh et al. | A multi-stream bi-directional recurrent neural network for fine-grained action detection | |
| Baraldi et al. | Gesture recognition in ego-centric videos using dense trajectories and hand segmentation | |
| Gall et al. | Hough forests for object detection, tracking, and action recognition | |
| CN109919977A (en) | A kind of video motion personage tracking and personal identification method based on temporal characteristics | |
| CN110569731A (en) | face recognition method and device and electronic equipment | |
| Ruiz-Santaquiteria et al. | Handgun detection using combined human pose and weapon appearance | |
| Ragheb et al. | Vihasi: virtual human action silhouette data for the performance evaluation of silhouette-based action recognition methods | |
| KR20210033940A (en) | How to Train Neural Networks for Human Facial Recognition | |
| CN110175553B (en) | Method and device for establishing feature library based on gait recognition and face recognition | |
| CN114863321B (en) | Automatic video generation method and device, electronic equipment and chip system | |
| Ranganatha et al. | An integrated robust approach for fast face tracking in noisy real-world videos with visual constraints | |
| Saeed | A framework for recognition of facial expression using HOG features | |
| Kayaoglu et al. | Affect recognition using key frame selection based on minimum sparse reconstruction | |
| CN111401313B (en) | Method, system and equipment for identifying and positioning physical education competition personnel | |
| CN110942003A (en) | Personnel track searching method and system | |
| CN112766162B (en) | Living body detection method, living body detection device, electronic equipment and computer readable storage medium | |
| CN113785304A (en) | Face recognition method and device | |
| CN109598201B (en) | Action detection method and device, electronic equipment and readable storage medium | |
| Hrkac et al. | Tattoo detection for soft biometric de-identification based on convolutional neural networks | |
| Zhao | Research on athlete behavior recognition technology in sports teaching video based on deep neural network | |
| CN113947781A (en) | Lost child identification method, lost child identification system, terminal equipment and storage medium | |
| Wang et al. | Tracking salient keypoints for human action recognition | |
| Abdullah et al. | A Survey of Face Recognition Systems | |
| Xu et al. | When handcrafted features and deep features meet mismatched training and test sets for deepfake detection | |
| CN111191563A (en) | Face recognition method and system based on data sample and test data set training |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |