Single Image Super-Resolution Using Sparse Representation on a K-NN Dictionary | |
Ning, Liu ; Shuang, Liang | |
2016 | |
关键词 | Super-resolution Sparse representation Restricted Boltzmann machine Binary encoding INTERPOLATION |
英文摘要 | This paper presents a new method of generating a high-resolution image from a low-resolution image. We use a sparse representation based model for low-resolution image patches. We use large patches instead of small ones of existing methods. The size of the dictionary must be large to guarantee its completeness. For each patch in the low-resolution image, we search for similar patches in the dictionary to obtain a sub-dictionary. To define the similarity and to speed up the searching process, we present a Restricted Boltzmann Machine (RBM) based binary encoding method to get binary codes for the low-resolution patches, and use Hamming distance to describe the similarity. With the KNN dictionary of each low-resolution patch, we use a sparse representation method to get its high-resolution version. Experimental results illustrate that our method outperforms other methods.; EI; CPCI-S(ISTP); liuning19880928@gmail.com; liangshuang12@pku.edu.cn; 169-178; 9680 |
语种 | 英语 |
出处 | SCI ; EI |
出版者 | 7th International Conference on Image and Signal Processing (ICISP) |
内容类型 | 其他 |
源URL | [http://hdl.handle.net/20.500.11897/436373] |
专题 | 数学科学学院 |
推荐引用方式 GB/T 7714 | Ning, Liu,Shuang, Liang. Single Image Super-Resolution Using Sparse Representation on a K-NN Dictionary. 2016-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论