Coupled dictionary learning method for image decomposition  

作　　者：LI YaFeng FENG XiangChu 

机构地区：[1]Department of Applied Mathematics,Xidian University [2]Department of Computer Science,Baoji University of Arts and Science

出　　处：《Science China(Information Sciences)》2013年第3期93-102,共10页中国科学（信息科学）（英文版）

基　　金：supported by National Natural Science Foundation of China(Grant Nos.60773209,60872138);Key Project of Chinese Ministry of Education(Grant No.211155);Key Project of Baoji University of Arts and Science(Grant No.ZK10171);Scientific Research Plan Project of Shaanxi Education Department(Grant No.12JK0550)

摘　　要：A novel variational model for image decomposition is proposed. Meanwhile a new cartoon-texture dictionary learning algorithm, which is guided by diffusion flow, is presented. Numerical experiments show that the proposed method has better performance than the existing algorithms in image decomposition and denoising.A novel variational model for image decomposition is proposed. Meanwhile a new cartoon-texture dictionary learning algorithm, which is guided by diffusion flow, is presented. Numerical experiments show that the proposed method has better performance than the existing algorithms in image decomposition and denoising.

关 键 词：dictionary learning cartoon-texture decomposition image denoising total variation 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]