一种基于多种特征融合的人脸识别算法  

A Face Recognition Algorithm Using Fusion of Multiple Features

作　　者：杨赛[1] 赵春霞[2] 刘凡[3] 陈峰[1] Yang Sai;Zhao Chunxia;Liu Fan;Chen Feng(School of Electrical Engineering, Nantong University, Nantong 226019;School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094;College of Computer and Information, Hohai University, Nanjing 210098)

机构地区：[1]南通大学电气工程学院,南通226019 [2]南京理工大学计算机科学与工程学院,南京210094 [3]河海大学计算机与信息学院,南京210098

出　　处：《计算机辅助设计与图形学学报》2017年第9期1667-1672,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：江苏省普通高校自然科学基金(16KJB520037);国家自然科学基金(61602150);江苏省自然科学基金(BK20151273);江苏省社会安全图像与视频理解重点实验室创新基金(30920140122007)

摘　　要：为了进一步提高词袋模型在人脸识别中的性能,提出一种融和多种特征所建立的词袋模进行人脸识别的算法.首先提取人脸图像中的若干局部特征,分别基于每种特征离线训练视觉词典,将每种局部特征映射到对应的高维中层语义空间中,然后使用空间金字塔模型得到每种特征的人脸图像描述,最后将各种特征拼接起来并使用线性SVM完成对人脸图像的分类判别.在多个公开数据库上的实验结果表明,该算法对人脸的姿态、表情变化以及面部遮挡具有更优良的鲁棒性,能够更好地解决小样本问题.In order to improve the performances of bag-of-features(BoF)in face recognition,a face recognition algorithm based on the fusion of multiple features under the framework of bag-of-features was proposed in this paper.This method firstly extracted different kinds of local features in face images to learn a corresponding over complete visual dictionary in advance.Then it mapped each local feature into a high dimensional mid-level semantic space,and employed spatial pyramid matching(SPM)to pool local coding features.Different kinds of features were concatenated as the final representation of images and classified by trained linear SVM.Experimental results on several benchmark datasets show that our method is more robust to position variations,expression changes and occlusion and can effectively solve the small training size problem.

关 键 词：人脸识别 局部特征 词袋模型 多种特征融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]