Face recognition method, device and equipment

A face recognition and face image technology, applied in the computer field, can solve the problem of low reliability of recognition results

Inactive Publication Date: 2019-12-03
SHENZHEN JIESHUN SCI & TECH IND
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of this application is to provide a face recognition method, device, equipment, and readable storage medium to solve the problem of facial features that only rely

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face recognition method, device and equipment
  • Face recognition method, device and equipment
  • Face recognition method, device and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] The following introduces Embodiment 1 of a face recognition method provided by the present application, see figure 1 , embodiment one includes:

[0055] S101. Obtain the face image of the current user;

[0056]This embodiment can be applied to the field of public security. Specifically, a video acquisition device is used to collect video data in preset public areas, image frames are intercepted from the video data, and image frames with human face areas are screened out through face detection, so as to As the face image in this embodiment. Wherein, the video collection device may be a visible light camera or a near-infrared camera, which is not limited in this embodiment.

[0057] S102, extracting the feature vector of the face image;

[0058] As a specific implementation manner, the key point detection is performed on the face image to obtain the key point detection result; the face image is corrected according to the key point detection result, and the corrected fa...

Embodiment 2

[0067] see figure 2 , embodiment two specifically includes:

[0068] S201. Acquire the current image frame, and extract the feature vector of the current image frame;

[0069] S202. Match the feature vector of the current image frame with the face feature of the registered user to determine the matching degree value;

[0070] S203. Determine whether there is a target face feature with a matching degree greater than the first preset threshold; if it exists, determine that the recognition is successful, and jump to S204; otherwise, do not do any processing;

[0071] S204. Determine the reliability score of the current image frame, and determine whether the reliability score is greater than a second preset threshold; if greater, jump to S205; otherwise, exit the process;

[0072] S205. Determine the pose data of the current image frame, and judge whether the pose data is within the preset range; if so, jump to S206; otherwise, exit the process;

[0073] The purpose of this st...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a face recognition method, a device, equipment and a readable storage medium. According to the method, the face image which is successfully recognized and meets a certain condition can be screened out in the face recognition process; and the pre-stored face features of the registered user are updated according to the feature vector of the face image, so that continuous updating of the face features of the registered user is realized, the influence of face appearance change caused by age change or accidental conditions on a face recognition process is eliminated, and thereliability of a face recognition result is improved.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a face recognition method, device, equipment and readable storage medium. Background technique [0002] Face recognition is the most commonly used identification method in the field of biometric identification. As a non-contact biometric technology, face recognition has the characteristics of visualization, convenience, and conformity to people's thinking habits. Therefore, in smart cities, It is widely used in public safety, rail transit, security control, finance and other fields, providing more convenience for these fields. [0003] The traditional face recognition scheme collects facial features during the user registration process as the identification basis for the subsequent recognition process. However, considering that the facial features of people will change with age, therefore, relying solely on the The collected face features are used for face recogn...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/00
CPCG06V40/172G06V40/168G06V40/50
Inventor 唐健黄海波陶昆巢时文
Owner SHENZHEN JIESHUN SCI & TECH IND
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap