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

Feature extraction method for face recognition

A feature extraction and face recognition technology, applied in the field of face recognition, can solve the problems of light changes or slight changes in expression interference, and cannot provide resolution, etc., to prevent light changes, improve the accuracy rate, and have good anti-interference effects.

Inactive Publication Date: 2017-10-20
SYSU CMU SHUNDE INT JOINT RES INST +1
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0015] (2) Easily disturbed by light changes or slight facial expressions
[0016] (3) The LBP value obtained by rotation has 36 possibilities for the corresponding original LBP value, which cannot provide a good resolution

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
  • Feature extraction method for face recognition
  • Feature extraction method for face recognition
  • Feature extraction method for face recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] A feature extraction method for face recognition, comprising the following steps:

[0047] S1: Let N training sample images be X=[x 1 , x 2 ,...,x N ]∈R d×N , x n ∈R d , where d is the number of eigenvalues, such as figure 1 As shown, the pixel difference vector (PDV) of the image is extracted; here, unlike LBP, it is not directly compared, and then set to 1 or 0, but a pixel is taken out, and then the value obtained by subtracting the center pixel from the domain pixel is used as The pixel value of this field point.

[0048] S2: Set the mapping matrix W to convert the pixel difference vector into a local binary code matrix B with dimension K, and then convert it into a feature histogram through the dictionary matrix D.

[0049] The binary code matrix of the training samples is:

[0050] B=0.5×(sgn(W T X)+1)∈{0,1} K×N (1)

[0051] where W T When XT X)=0, otherwise, sgn(W T X) = 1;

[0052] S3: Make matrix A=[a 1 , a 2 ..., a N ] is the corresponding co...

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 present invention provides a feature extraction method for face recognition, which adopts the method of synchronous local binary feature learning and coding (SLBFLE) to extract a pixel difference vector of a face image, sets a mapping matrix W to convert the pixel difference vector into a low dimension local binary feature matrix B, converts a dictionary matrix D into a feature histogram and optimizes the mapping matrix W, the dictionary matrix D and a coefficient matrix A through an iterative method to obtain the feature histogram. The method can better prevent the influence of light variation and expression variation, improve the accuracy of face recognition, and have better anti-interference than that of the LBP method. The method is more suitable for the places with complex environments, and can be better applied to the classroom face check-in system feature extraction.

Description

technical field [0001] The present invention relates to the field of face recognition, and more specifically, to a feature extraction method for face recognition. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. A series of related technologies that use a video camera or camera to collect images or video streams containing human faces, automatically detect and track human faces in the images, and then perform facial recognition on the detected faces, usually also called portrait recognition and facial recognition. [0003] The existing LBP (Local Binary Patterns) face feature extraction method is analyzed from the perspective of face texture. The texture feature of a pixel in a face image has a close relationship with this point and its surrounding pixels, that is, a point The characteristics of are determined by this point and its domain points. LBP constructs a relationship that measure...

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
CPCG06V40/168G06V40/172G06V10/507
Inventor 胡建国黄家诚林培祥晏斌邓成谦李凯祥
Owner SYSU CMU SHUNDE INT JOINT RES INST
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