重庆邮电大学学报（自然科学版）2011，Vol.23Issue(3)：355-362,8.DOI:10.3979/j.issn.1673-825X.2011.03.021
基于Gabor特征和EHMM的人脸识别方法
Face recognition based on Gabor feature and EHMM
摘要
Abstract
This paper brings forward a new face recognition method, aiming at improving the inefficient robustness of the traditional face recognition method when factors like expression, gesture, and illumination are involved. When it comes to feature extraction, this new method will first extract the Gabor feature of a human face, and then assemble the similar features with DCT( discrete cosine transform), and last, sieve out the DCT coefficients which can mostly represent each areas of human face with PCA( principal component analysis). When it comes to recognition method, it adapts EHMM (embedded hidden markov model), and improves the EHMM human face model according to the understanding of cognitive structure of human face. Comparative experiments show that the proposed method has a high recognition rate and a low complex rate. And it has excellent robustness, which proves that it can be easily applied to engineering projects.关键词
人脸识别/嵌入式隐马尔科夫模型/Gabor小波变换/离散余弦变换Key words
face recognition/ embedded hidden markov model(EHMM)/ Gabor wavelets transform/ discrete cosine transform (DCT)分类
信息技术与安全科学引用本文复制引用
杨勇,田侃..基于Gabor特征和EHMM的人脸识别方法[J].重庆邮电大学学报（自然科学版）,2011,23(3):355-362,8.基金项目
重庆市杰出青年基金(2008BA2041) （2008BA2041）
重庆邮电大学基金(A2009-26) （A2009-26）
重庆市计算机网络与通信技术重点实验室开放基金(CY-CNCL-2009-02) （CY-CNCL-2009-02）
