基于自适应加权子模式判别邻域投影的人脸识别方法  

Face Recognition Method Based on Adaptively Weighted Sub-pattern Discriminant Neighborhood Projection

作　　者：杨柳 陈丽敏 易玉根 YANG Liu;CHEN Li-min;YI Yu-gen(School of Computer Science and Information Technology,Mudanjiang Normal University,Mudanjiang,Heilongjiang 157012,China;School of Software,Jiangxi Normal University,Nanchang 330022,China)

机构地区：[1]牡丹江师范学院计算机与信息技术学院,黑龙江牡丹江157012 [2]江西师范大学软件学院,南昌330022

出　　处：《计算机科学》2019年第10期307-310,共4页Computer Science

基　　金：黑龙江省自然科学基金项目(LH2019F051)资助

摘　　要：人脸识别是图像处理和模式识别中的研究热点问题之一,对此,文中提出了一种基于自适应加权子模式判别邻域投影的人脸识别方法。该方法首先将人脸图像划分成较小的人脸图像块,并将相同位置的子图像构建成子模式集;其次,为了提高低维特征的判别能力,同时考虑数据的局部结构信息和类别标签信息,对于每个子模式集,构建一个局部判别邻域图;最后,考虑不同子模式集对人脸图像识别的贡献,引入一个非负权值向量结合所有子模式集的局部散度矩阵,以找出同幅人脸图像的不同子图像之间的互补信息。实验结果表明,相比于其他方法,所提方法的性能更优。Face recognition is one of the hot topics in the image processing and pattern recognition,an adaptively weighted sub-pattern discriminant neighborhood projection method was proposed for face recognition.Firstly,the face images are divided into several small blocks,and the sub images with same position are used to construct the sub-pattern set.Then,in order to improve the discrimination ability of low dimensional features,the local data structure information and the label information of each sub pattern set are employed to construct a local discriminant neighborhood graph.Finally,for taking different contribution of different sub-pattern into account,a non negative weight vector is introduced to combine with the local scatter matrices of all sub-pattern sets,in order to find out the complementary information between different sub-image of the same faceimage.The experimental results show that the proposed method is superior to other methods.

关 键 词：人脸识别 子模式 自适应加权 局部结构 标签信息 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]