| Image super-resolution via saliency sparse representation | |
| Zhang, Xue Jun; Hu, Bing Liang | |
| 2014 | |
| 会议录名称 | Measurement Technology and its Application III |
| 页码 | 659-662 |
| 出版者 | Trans Tech Publications Ltd |
| 产权排序 | 1 |
| 摘要 | The paper proposes a new approach to single-image super resolution (SR), which is based on sparse representation. Previous researchers just focus on the global intensive patch, without local intensive patch. The performance of dictionary trained by the local saliency intensive patch is more significant. Motivated by this, we joined the saliency detection to detect marked area in the image. We proposed a sparse representation for saliency patch of the low-resolution input, and used the coefficients of this representation to generate the high-resolution output. Compared to precious approaches which simply sample a large amount of image patch pairs, the saliency dictionary pair is a more compact representation of the patch pairs, reducing the computational cost substantially. Through the experiment, we demonstrate that our algorithm generates high-resolution images that are competitive or even superior in quality to images produced by other similar SR methods. © (2014) Trans Tech Publications, Switzerland. |
| 作者部门 | 光谱成像技术实验室 |
| 收录类别 | EI |
| 语种 | 英语 |
| ISSN号 | 16609336 |
| 文献类型 | 会议论文 |
| 条目标识符 | http://ir.opt.ac.cn/handle/181661/22581 |
| 专题 | 光谱成像技术研究室 |
| 推荐引用方式 GB/T 7714 | Zhang, Xue Jun,Hu, Bing Liang. Image super-resolution via saliency sparse representation[C]:Trans Tech Publications Ltd,2014:659-662. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
| Image super-resoluti（274KB） | 限制开放 | CC BY-NC-SA | 请求全文 | |||
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