Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for intelligent face recognition

A technology of intelligent recognition and recognition, which is applied in the field of intelligent face recognition, can solve the problems of unrecognizable, face recognition of people to be recognized, area distortion, etc., and achieve the effect of high accuracy

Active Publication Date: 2021-07-13
广州利科科技有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to overcome the above-mentioned problems in the prior art, and provides a face intelligent recognition method, which is used to solve the distortion or unrecognizability of some areas of the image caused by the adjustment of the face posture in traditional face recognition, which in turn leads to The problem that the face of the person to be recognized cannot be correctly recognized

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
  • A method for intelligent face recognition
  • A method for intelligent face recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Such as figure 1 and figure 2 As shown, the present embodiment provides a method for intelligent face recognition, the method comprising:

[0059] Obtain the image to be recognized and recognize the person to be recognized in the image;

[0060] When the person to be identified cannot be identified, the face image of the person to be identified is selected as the original image;

[0061] Locating and tracking the person to be identified through the image acquisition source of the original image;

[0062] Based on the acquisition time of the original image and the same image acquisition method, at least one additional face image of the person to be identified that is closest to the original image and the original image are obtained to form an original atlas, according to the orientation of the positioning and tracking. The auxiliary face collector collects at least one face image of the person to be recognized from different angles as a correction atlas;

[0063] By...

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

A method for intelligent face recognition, the method comprising: selecting an original image when the person to be identified cannot be identified; locating and tracking the person to be identified; acquiring the face image and the original image to form an original atlas, collecting At least one face image of the person to be recognized from different angles is a corrected atlas; by adjusting the face poses of the face images in the original atlas and the corrected atlas, a missing recognition sample set including frontal face image samples is obtained and The complete face contour area; according to the complete face contour area, the face samples in the missing recognition sample set are divided into blocks to form a block area set; marked as the selected block; after the corrected image is obtained by using the selected block restoration, the corrected image Perform face recognition. It solves the problem that some areas of the image are distorted or unrecognizable after the face posture is adjusted in the traditional face recognition, which leads to the problem that the face of the person to be recognized cannot be correctly recognized.

Description

technical field [0001] The present invention relates to the field of human face image recognition, and more particularly, relates to a method for intelligent human face recognition. Background technique [0002] With the help of the networking of cameras and computers or some independent integrated tools, face recognition technology has become a very popular and commonly used technology in modern people's lives. With the help of face recognition technology, people can remotely or intelligently complete face recognition. However, traditional face recognition is very dependent on the orientation of the person to be recognized within a certain range and the shooting angle of the camera. In the acquired images containing different face poses, the recognition rate of face recognition often decreases exponentially due to the excessive angle. [0003] In view of the above problems, the most commonly used in the prior art is to focus on the conversion between the two-dimensional a...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/161G06V40/168
Inventor 金耀初何卫灵刘华
Owner 广州利科科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com