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

SVD (Singular Value Decomposition)-based method for extracting joint features of multi-source face images

A singular value decomposition and joint feature technology, which is applied in the field of face image feature extraction, can solve the problems that the face information cannot be accurately expressed, and the samples cannot be clearly and accurately represented.

Active Publication Date: 2018-05-15
广东世纪晟科技股份有限公司
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] A single sample cannot clearly and accurately represent the information of the current face image. For the same face, different positions, lighting, and angles can form a series of different images, and such images represent the same face. , it is obviously impossible to accurately express the face information

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
  • SVD (Singular Value Decomposition)-based method for extracting joint features of multi-source face images
  • SVD (Singular Value Decomposition)-based method for extracting joint features of multi-source face images
  • SVD (Singular Value Decomposition)-based method for extracting joint features of multi-source face images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0019] Such as figure 1 As shown, the method for joint feature extraction of multi-source face images based on singular value decomposition of this embodiment includes the following steps: A: Extract grayscale, binary, and intuitive feature maps of multi-source face samples, and merge them into Joint feature; B: Extract the attribute value of the joint feature, calculate the reverse integral graph, use the singular decomposition reverse integral graph to obtain the singular value of the reverse integral graph, and use the singular value of the reverse integral graph to calculate the singular value matrix of the reverse integral graph ; C: Use the reverse integral graph singular value matrix and three-line interpolation to accelerate the feature calculation to obtain the directional gradient histogram; D: Use the kernel nearest neighbor convex hull algorithm of the local mean to reduce the dimensionality of the directional gradient histogram feature.

[0020] Each step is explained...

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 aims to provide an SVD (Singular Value Decomposition)-based method for extracting joint features of multi-source face images so as to increase the recognition rate of face recognition. The method comprises the following steps of: A, extracting the grayscale image, the binary image and the intuitive feature image of a human face sample to serve as data sources and merging into a jointfeature; B, extracting the attribute value of the joint feature, calculating a reverse integral image, carrying out singular value decomposition on the reverse integral image to obtain the singular value of the reverse integral image and calculating a singular value matrix of the reverse integral image by utilizing the singular value of the reverse integral image; C: accelerating the feature calculation by utilizing the singular value matrix of the reverse integral image and trilinear interpolation to obtain a high-dimensional directional gradient histogram; and D: carrying out feature dimension reducing calculation on the directional gradient histogram by utilizing a local mean-based kernel nearest neighbor convex hull algorithm to obtain a low-dimensional face image directional gradienthistogram feature.

Description

Technical field [0001] The invention relates to a method for extracting features of a face image. Background technique [0002] In the rapid development of modern science and technology, personal identification technology is of great significance in the fields of finance, security, justice, and investigation. Due to the comprehensive popularization of network technology, information security has also shown unprecedented importance. In security, judicial and other fields, accurate identification is required. The technology of identifying personal identity through image processing and pattern recognition has the advantages of strong reliability, fast recognition speed, convenient method, low price, good naturalness and acceptability, etc., so it has become the focus of technology developers , Used in various fields. However, with the development of science and technology in society, people's needs no longer stay in functional requirements, but more are the pursuit of efficient an...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V40/168G06V10/50G06F18/251
Inventor 温峻峰李鑫江志伟谢巍杜海江张浪文吴伟林夏欢陈庭
Owner 广东世纪晟科技股份有限公司
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