基于分块KPCA集成的人脸民族特征提取研究  

Research on Extraction about Ethnic Features of Face Images Based on Integrated Feature and BKPCA

作　　者：刘文辉[1,2] 许瑞[2] 刘华咏[1] 马光春[3] 

机构地区：[1]华中师范大学计算机学院,武汉430079 [2]新疆教育学院信息科学与技术分院,乌鲁木齐830043 [3]新疆喀什师范学院信息工程技术系,喀什844007

出　　处：《计算机科学》2014年第9期294-296,319,共4页Computer Science

基　　金：新疆维吾尔自治区高等学校科学研究计划资助项目"FSRPHEXJ"(XJEDU2011I45)资助

摘　　要：为了实现人脸图像民族特征提取,提出了一种分块集成KPCA的特征提取方法。考虑到利用全局特征与局部特征的互补性能够更好地反映信息的本质,先以KPCA提取整体图像特征,然后使用KPCA对各个分块进行局部特征提取,再组合为民族特征,最后使用设计的Boosting-RBF分类器进行民族分类识别。实验以构建的少数民族人脸样本库为研究对象,对维吾尔族、柯尔克孜族、蒙古族、塔吉克族的人脸图像进行民族特征提取。实验结果表明:提取的人脸民族特征,可以对人脸图像进行较准确的民族分类识别。A method based on the extracting block integrated features of KPCA was presented for the extraction of the ethnic features of face images. Because the complementarity of global features and local features can better reveal the essence of information, firstly,KPCA was used to the extract the global features of face image and the local feature of each sub block, secondly these features was combined into ethnic features, finally the Boosting-RBF classifier designed in the paper was used to identify image samples of ethnic face. The experiment subjects are a constructed Minorities face image database in this paper. The experimental results show that the extracted ethnic features in this paper can identify accurately the ethnic group to which the face image belongs.

关 键 词：民族脸特征 特征提取 分块核主元分析 民族识别 径向基神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]