Constrained Sparse Concept Coding algorithm with application to image representation

作     者：Shu, Zhenqiu Zhao, Chunxia Huang, Pu 

作者机构：Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Jiangsu Peoples R China 

出 版 物：《KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS》 (KSII Trans. Internet Inf. Syst.)

年 卷 期：2014年第8卷第9期

页      面：3211-3230页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China [61272220, 61101197] Jiangsu Province Fund for Graduate Innovation Program [CXLX13 19] Natural Science Foundation of Jiangsu Province of China [BK2012399] Jiangsu Key Laboratory of Image and Video Understanding for Social Safety 

主　　题：Sparse coding label information semi-supervised constraints manifold kernelized 

摘      要：Recently, sparse coding has achieved remarkable success in image representation tasks. In practice, the performance of clustering can be significantly improved if limited label information is incorporated into sparse coding. To this end, in this paper, a novel semi-supervised algorithm, called constrained sparse concept coding (CSCC), is proposed for image representation. CSCC considers limited label information into graph embedding as additional hard constraints, and hence obtains embedding results that are consistent with label information and manifold structure information of the original data. Therefore, CSCC can provide a sparse representation which explicitly utilizes the prior knowledge of the data to improve the discriminative power in clustering. Besides, a kernelized version of our proposed CSCC, namely kernel constrained sparse concept coding (KCSCC), is developed to deal with nonlinear data, which leads to more effective clustering performance. The experimental evaluations on the MNIST, PIE and Yale image sets show the effectiveness of our proposed algorithms.