集体表示分类方法及在人脸识别中的应用  

Joint-collective representation classification method and application in face recognition

作　　者：马腾飞[1] 王丽平[1] MA Tengfei;WANG Liping(College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China)

机构地区：[1]南京航空航天大学理学院,南京210016

出　　处：《计算机工程与应用》2017年第12期16-20,98,共6页Computer Engineering and Applications

基　　金：国家自然科学基金(No.11471159;No.61661136001)

摘　　要：近年来,基于表示的人脸图像识别方法吸引了众多学者的关注,如稀疏表示分类方法(Sparse Representation based Classification,SRC)、协作表示方法(Collaborative Representation based Classification,CRC)等。这些方法均利用单张图像的表示信息进行识别,而忽略了集体图像之间的关联性,容易存在信息不足的缺陷。为了能够充分利用多张人脸图像的相互关系,提出了一类集体表示分类方法。该方法将多张待识别图像映射为一个稀疏表示矩阵,并对每类测试图像集体重构,以最小残差为准则对每类人脸图像集分类。这种方法通过同时表示多张图像,关注到不同图像之间的相似与不同,获取到同一主体的更多信息,从而提高识别正确率。尤其在只有多张侧脸图像而无正脸图像的情况下,集体表示分类方法更能发挥优势,在两个公开人脸图像数据集上的实验结果也验证了该方法的有效性。Recently,representation-based classifications,such as Sparse Representation Classification(SRC),CollaborativeRepresentation Classification(CRC),etc.have attracted extensive attention.These methods use a single picture torecognize the testing subject but ignore the relationship among a collection of pictures which lead to inadequate details.To take advantage of the correlation of multiple images,this paper presents a collective representation classification inface recognition.The new method uses a matrix to represent all the testing images then the most compact representationerror is evaluated for classification.Multi-representation helps to take account of the similarity and difference hidden inthe testing image-set.Especially when the image set includes more side-face images than frontal ones,Joint-collectiveRepresentation Classification(JRC)outperforms the state-of-the-art method which is also validated by the practicalexperiments in two public databases.

关 键 词：集体表示 人脸识别 稀疏优化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]