基于公共矢量的总间隔v最小类内方差支持向量机在噪音人脸图像分类中的应用  

Total margin v minimum class variance support vector machines based on common vectors for noisy face classification

作　　者：杨冰[1] 王士同[1] 

机构地区：[1]江南大学信息工程学院,江苏无锡214122

出　　处：《山东大学学报（理学版）》2010年第11期5-11,共7页Journal of Shandong University(Natural Science)

基　　金：国家高技术研究发展计划(863计划)基金资助项目(2007AA1Z158);国家自然科学基金资助项目(60704047);国家自然科学基金重大研究计划资助项目(9082002)

摘　　要：为提高噪音人脸图像分类问题中的抗噪性能,在综合最小类内方差支持向量机(minimum class variance support vector machines,MCVSVMs)和总间隔v-支持向量机(total margin v support vector machine,TM-v-SVM)的优点的基础上,提出了基于公共矢量的总间隔v最小类内方差支持向量机(Total margin v minimum class variance support vector machines based on common vectors,TM-v-M(CV)2SVMs)。受公共矢量(commonvectors,CVs)的启发,引入了散度矩阵以进一步提高算法的分类性能和抗噪性能,并给出了TM-v-M(CV)2SVMs的推导过程。经实验证明,在噪音人脸图像的分类问题中,TM-v-M(CV)2SVMs获得了比MCVSVMs和TM-v-SVM更好的分类性能和抗噪性能。Algorithm total margin v minimum class variance support vector machines based on common vectors （ TM-v- M （CV）2 SVMs ） were presented for noisy face recognition, which integrates the advantages of minimum class variance support vector machines（MCVSVMs） and total margin v support vector machine（ TM-v-SVM）. Based on common vec- tors （CVs）, the divergence matrix was introduced to improve the classification and anti-noisy performances of noisy face classification, and TM-v-M （CV）2 SVMs derivation was given. The experimental results about noisy face classifi- cation showed that the proposed TM-v-M （CV）2 SVMs had better classification performance than both the MCVSVMs and TM-v-SVM.

关 键 词：支持向量机 最小类内方差支持向量机 总间隔v-支持向量机 判别公共矢量 公共矢量 人脸识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]