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

Face recognition optimization method based on SGASEN algorithm

A face recognition and optimization method technology, applied in the direction of character and pattern recognition, calculation, gene model, etc., can solve the problems of high complexity and low recognition rate, achieve the effect of reducing complexity and improving classification accuracy

Inactive Publication Date: 2017-08-04
BEIJING UNIV OF TECH
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is to propose a kind of Selective Ensemble Learning Method based on Similarity Improved Genetic Algorithm based on Similarity Improved Genetic Algorithm for the problems of high complexity and low recognition rate in the existing face recognition technology. , SGASEN) applied to face recognition

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 optimization method based on SGASEN algorithm
  • Face recognition optimization method based on SGASEN algorithm
  • Face recognition optimization method based on SGASEN algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Provide the explanation of each detailed problem involved in the technical scheme of this invention below in detail:

[0025] Before proposing a new method, first of all, Zhou et al. (Zhi-Hua Zhou, Jianxin Wu, WeiTang. 263) proposed a theoretical analysis of selective ensemble learning, which mainly analyzes the selective theory for binary classification problems.

[0026] Assuming m training samples, their expected output is [d 1 , d 2 ,···,d m ] T , where d j is the expected result of the jth sample. f={f 1 ,f 2 ,···,f N} is the set of base classifiers trained by the sample set, where N is the number of base classifiers, f i is the i-th base classifier, and its classification result is [f i1 ,f i2 ,···,f im ] T , f ij That is, the output result of the i-th base classifier for the j-th sample. where d j ∈{-1,+1}(j=1,2,···,m), f ij ∈{-1,+1} (i=1,2,...,N; j=1,2,...,m). Obviously, when the i-th base classifier correctly classifies the j-th sample, there ...

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 optimization method based on an SGASEN algorithm. First, the features of a face image are extracted. Then, recognition and classification are carried out using an SGASEN algorithm. In view of the problem that there are a large number of invalid cross operations on population in the SGASEN algorithm, a regression tree is used as a base classifier, and computationally simple Jaccard similarity detection is used before cross operation, so that cross operations on similar individuals are reduced, and the population is more diverse. In view of the fact that the number of base classifiers is not limited in the SGASEN algorithm, generalization error and the number of base classifiers are considered in a fitness function, and genetic evolution is carried out using an optimal retention strategy. Finally, a strong classifier with strong generalization ability and fewer base classifiers is obtained, and the accuracy of face recognition is improved.

Description

technical field [0001] The invention belongs to the technical field of machine learning and pattern recognition, and uses a training data set to construct a prediction method with strong generalization ability, in order to achieve accurate estimation of new unknown objects. Background technique [0002] Face recognition technology is the main technology in image processing, but the low recognition rate has always been an important reason that hinders the wide application of face recognition technology. The research found that the accuracy rate can be improved through the method of integrated learning. Ensemble learning is a learning model of a strong classifier formed by the weighted combination of multiple base classifiers or weak classifiers. The goal of integration is to combine several base classifiers to improve the problem of insufficient predictive ability on a single classifier, so that it has better generalization ability and robustness. However, in the process of...

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): G06K9/00G06K9/62G06N3/12
CPCG06N3/126G06V40/168G06V40/172G06F18/2135G06F18/254G06F18/259G06F18/24
Inventor 杨新武张翱翔袁顺
Owner BEIJING UNIV OF TECH
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