Image clustering via sparse representation | |
Jiao, Jun ; Mo, Xuan ; Shen, Chen | |
2009 | |
英文摘要 | In recent years, clustering techniques have become a useful tool in exploring data structures and have been employed in a broad range of applications. In this paper we derive a novel image clustering approach based on a sparse representation model, which assumes that each instance can be reconstructed by the sparse linear combination of other instances. Our method characterizes the graph adjacency structure and graph weights by sparse linear coefficients computed by solving 1-minimization. Spectral clustering algorithm using these coefficients as graph weight matrix is then used to discover the cluster structure. Experiments confirmed the effectiveness of our approach. ? 2010 Springer-Verlag Berlin Heidelberg.; EI; 0 |
语种 | 英语 |
DOI标识 | 10.1007/978-3-642-11301-7_82 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/412845] |
专题 | 软件与微电子学院 |
推荐引用方式 GB/T 7714 | Jiao, Jun,Mo, Xuan,Shen, Chen. Image clustering via sparse representation. 2009-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论