MP-based Image Sparse Decomposition: Realized in a Lower Space
YIN Zhong-ke~1, WANG Jian-ying~1, Pierre Vandergheynst~2 (1. School of Computer & Communication Engineering, Southwest Jiaotong University, Chengdu 610031,China;2. Signal Processing Lab., Swiss Federal Institute of Technology at Laussane, Switzerland)
To overcome the key problem in image sparse decomposition by Matching Pursuit(MP), a fast algorithm is presented which realizes high space search in a lower space. The validity of this newly proposed algorithm is confirmed by the experimental result.