Non-negative matrix factorization based on double sparsity K-SVD

摘要：

　　This paper presents a novel non-negative matrix factorization algorithm based on double sparsity K-SVD.It keeps the good parts-based representation.And meanwhile it has a well sparsity as sparse coding.The influences given by different initialization condition have been successfully overcome.Compared with other algorithms, the algorithm proposed is much faster.This dissertation demonstrates the advantages of the proposed algorithm by simulator experimentation.

关键词： double spadsity K-SVD non-negative matrix factorization

作者: Zheng Hong Li Zhen Li Zhao

作者单位: School of Automation Science and Electrical Engineering,Beihang University,Beijing 100191;Science an School of Automation Science and Electrical Engineering,Beihang University,Beijing 100191

会议类型: 国际会议

会议名称: the 3nd International Conference on Digital Manufacturing & Automation (第三届数字制造与自动化国际会议(ICDMA 2012))

会议地点: 桂林

会议语种:英文

页码: 352-355

在线出版日期: 2012-08-01（万方平台首次上网日期，不代表论文的发表时间）