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

Face recognition method of attitude robust

A face recognition and posture technology, applied in the field of face recognition, can solve the problems of recognition performance degradation and achieve the effects of reducing equipment cost and power consumption, reducing sensitivity, and improving recognition performance

Active Publication Date: 2010-06-30
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF0 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the defect that the existing face recognition technology is sensitive to gesture differences and cause the recognition performance to decline, the present invention provides a pose-robust face recognition method

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 of attitude robust
  • Face recognition method of attitude robust
  • Face recognition method of attitude robust

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] A pose-robust face recognition method provided by the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] figure 1 A process flow of a gesture-robust face recognition method based on ridge regression according to an embodiment of the present invention is shown. Such as figure 1 As shown, the method includes: detecting the human face region of the input human face image, locating its facial feature points and carrying out normalization processing (step 10) to the human face region; estimating the posture of the input human face, and obtaining the posture of the input human face Angle or posture category (step 20); Extract the feature (step 30) of the people's face area after normalization processing; According to the feature of the people's face area extracted and based on the acquired attitude angle or the face data of attitude category coupling Using the ridge regression model to obtain li...

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 provides a face recognition method of attitude robust. The method comprises the following steps of: detecting a face region of an input face image, locating a face key characteristic point and carrying out unitary processing on the face region; evaluating the attitude of an input face, and obtaining the class of the attitude of the input face; extracting the characteristic of the face region subjected to the unitary processing; obtaining a linear combination's coefficient by utilizing a ridge regression model according to the extracted characteristic of the face region and the face data coupled on the basis of the attitude class; and inputting the linear combination's coefficient into a classifier to obtain the result of face recognition. By applying the method, the sensibility of face recognition to attitude difference is lowered, and the adaptive capacity of face recognition to various application scenarios is enhanced while better recognition performance is kept.

Description

technical field [0001] The present invention relates to the technical field of face recognition, and more specifically, the present invention relates to a pose-robust face recognition method. Background technique [0002] Face recognition technology is a recognition technology that uses computers to analyze human faces to identify human biological characteristics. Its content covers computer vision, pattern recognition, graphics and cognitive science and other disciplines. Compared with obtaining other human biological characteristics, since the acquisition of human face images does not require the active cooperation of users, and the recognition is stronger, the ease of obtaining human face images in practical applications is much greater than that of other human biological characteristics. Acquisition makes the face recognition technology have a very broad application prospect. [0003] The easy acquisition of face images not only brings broad application prospects for fa...

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): G06K9/00G06K9/46
Inventor 李安南山世光陈熙霖
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
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