Super-Resolution based on Improved Sparse Coding

摘要：

A sparse dictionary model for image super-resolution is presented, which unifies the feature patches of high-resolution (HR) and low-resolution images using sparse dictionary coding. This method builds a sparse association between middle-frequency and high-frequency image components and realizes simultaneously match searching and optimization methods. Comparison with sparse coding method shows sparse dictionary is more compact and effective. Sparse K-SVD algorithm is applied for optimization to speed up sparse coding. Some experiments with real images show that our method outperforms other learning-based super-resolution algorithms.

关键词： super resolution learning-based sparse dictionary

作者: Li Min Li ShiHua Wang Fu Le Xiang Li Min Jin Hong Jiang LianJun

作者单位: Institute of Geo-Spatial Information Science and Technology University of Electronic Science and Tec Department of Scientific Research Guilin Airforce Academy Guilin, China

会议类型: 国际会议

会议名称: The 2010 International Conference on Computer Application and System Modeling(2010计算机应用与系统建模国际会议 ICCASM 2010)

会议地点: 太原

会议语种:英文

页码: 398-401

在线出版日期: 2010-10-22（万方平台首次上网日期，不代表论文的发表时间）