Intelligent nonconvex compressive sensing using prior information for image reconstruction by sparse representation

详细信息    查看全文

• 作者：Qiang Wang ^{wangqiang@hit.edu.cn}Author Vitae ; Dan Li ; ^{lidanhit@163.com}Author Vitae ; Yi Shen ^{shen@hit.edu.cn}Author Vitae
• 关键词：Image reconstruction ; Sparse representation ; Nonconvex l0 minimization ; Intelligent optimization ; Prior information
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：8 February 2017
• 年：2017
• 卷：224
• 期：Complete
• 页码：71-81
• 全文大小：2735 K
• 卷排序：224

文摘

We exploit the nonlocal self-similarity property to obtain the prior information. We extract more information to enrich the prior information to enhance the guidance accuracy based on the property that image blocks spatially nearby share the similar structures. We combine the superiorities of intelligent optimization algorithm with matching strategies of greedy algorithms to solve the nonconvex l0 minimization essentially. The developed INCS can reconstruct the original image accurately with fewer measurements.