Employing structural and statistical information to learn dictionary(s) for single image super-resolution in sparse domain
作者：
Highlights：
• A dictionary learning approach for super-resolving an image is proposed.
• The approach involves structural as well as statistical information of image patches.
• The same information is checked to assign a dictionary during reconstruction.
• Suitable non-smooth patches are only considered for super-resolution.
• An edge preserving constraint preserves the edge during super-resolution.
摘要
Highlights•A dictionary learning approach for super-resolving an image is proposed.•The approach involves structural as well as statistical information of image patches.•The same information is checked to assign a dictionary during reconstruction.•Suitable non-smooth patches are only considered for super-resolution.•An edge preserving constraint preserves the edge during super-resolution.
论文关键词：Sparse representation,Dictionary,Edge orientation,Clustering,Edge preserving constraint,Super-resolution
论文评审过程：Received 18 February 2016, Revised 23 August 2016, Accepted 23 August 2016, Available online 25 August 2016, Version of Record 19 September 2016.
论文官网地址：https://doi.org/10.1016/j.image.2016.08.006
