Open AccessImage restoration based on adaptive switching between synthesis and analysis sparse regularisation
Author(s) -
Chen Huahua,
Xue Jiling,
Lu Yu,
Guo Chunsheng
Publication year - 2020
Publication title -
the journal of engineering
Language(s) - English
Resource type - Journals
ISSN - 2051-3305
DOI - 10.1049/joe.2019.0810
Subject(s) - computer science , sparse approximation , image (mathematics) , dual (grammatical number) , eigenvalues and eigenvectors , principal component analysis , image restoration , sparse matrix , pattern recognition (psychology) , algorithm , artificial intelligence , inverse problem , inverse , mathematical optimization , image processing , mathematics , art , mathematical analysis , physics , literature , quantum mechanics , gaussian , geometry
Both synthesis and analysis sparse regularisation have been successfully applied to solve various inverse vision problems. The authors find an optimisation model to combine the power of the dual sparse prior models for image restoration. Specifically, for each local patch, adaptive switching on using synthesis or analysis sparse regularisation is performed for better restoration quality. In addition, cluster‐specific synthesis and analysis sub‐dictionary learning, based on principal component analysis method and sequential minimal eigenvalues algorithm, is incorporated into the joint sparse models to achieve maximum indices gains. The efficient alternating strategy is exploited to solve the optimisation problem. Experimental results highlight the superiority of the proposed approach compared with the state‐of‐the‐art methods, especially in terms of better image structures preservation.