首页 | 本学科首页   官方微博 | 高级检索  
     检索      

利用粒子群优化的人脸特征提取识别算法
引用本文:温浩,郭崇慧.利用粒子群优化的人脸特征提取识别算法[J].西安交通大学学报,2010,44(4).
作者姓名:温浩  郭崇慧
作者单位:1. 西安电子科技大学综合业务网理论及关键技术国家重点实验室,710071,西安
2. 大连理工大学系统工程研究所,116024,辽宁大连
摘    要:针对如何提高人脸图像识别率问题,提出了利用粒子群优化(PSO)的人脸特征提取识别算法.采用小波变换和张量主成分分析(PCA)方法对人脸图像进行特征提取,利用PSO对提取的特征进行加权处理,根据特征的每一维元素的聚类正确率进行优化选择,从而达到对人脸提取关键性特征的目的.实验结果表明,所提算法能减小光照、表情和姿态变化的影响,在英国曼彻斯特科技大学人脸数据库上的识别率比张量PCA方法提高了12.75%.

关 键 词:小渡变换  张量主成分分析  粒子群优化  人脸识别

Face Recognition with Features Extraction Based on Particle Swarm Optimization
WEN Hao,GUO Chonghui.Face Recognition with Features Extraction Based on Particle Swarm Optimization[J].Journal of Xi'an Jiaotong University,2010,44(4).
Authors:WEN Hao  GUO Chonghui
Institution:WEN Hao1,GUO Chonghui2(1.State Key Laboratory of Integrated Service Networks,Xidian University,Xi\'an 710071,China,2.Institute ofSystems Engineering,Dalian University of Technology,Dalian,Liaoning 116024,China)
Abstract:A face recognition algorithm with optimal features extraction based on particle swarm optimization (PSO) is proposed to enhance the recognition rate. Features of each face image are extracted by using the wavelet transformation and the tensor principal component analysis (PCA) algorithm. Weights of the features' elements are then determined using PSO according to the right clustering rate of each element,so that the object to extract the key features of the faces can be realized. Experimental results on the...
Keywords:wavelet transforms  tensor principal component analysis  particle swarm optimiza-tion  face recognition
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号