Image super-resolution enhancement based on online learning and blind sparse decomposition
文献类型：会议论文
| 作者 | Jinzheng Lu; Qiheng Zhang; Zhiyong Xu; Zhenming Peng |
| 出版日期 | 2011 |
| 会议名称 | Proc. of SPIE |
| 会议日期 | 2011 |
| 卷号 | 8004 |
| 页码 | 80040B |
| 通讯作者 | Jinzheng Lu |
| 中文摘要 | This paper presents a different learning-based image super-resolution enhancement method based on blind sparse decomposition, in order to improve its resolution of a degraded one. Firstly, sparse decomposition based image super-resolution enhancement model is put forward according to the geometrical invariability of local image structures under different conditions of resolution. Secondly, for reducing the complexity of dictionary learning and enhancing adaptive representation ability of dictionary atoms, the over-complete dictionary is constructed using online learning fashion of the given low resolution image. Thirdly, since the fixed sparsity of the conventional matching pursuit algorithms for sparse decomposition can not fit all types of patches, the approach to sparse decomposition with blind sparsity can achieve relatively higher accurate sparse representation of an image patch. Lastly, atoms of high resolution dictionary and coefficients of representation of the given low-resolution image are synthesized to the desired SR image. Experimental results of the synthetic and real data demonstrate that the suggested framework can eliminate blurring degradation and annoying edge artifacts in the resulting images. The proposed method can be effectively applied to resolution enhancement of the single-frame low-resolution image. |
| 英文摘要 | This paper presents a different learning-based image super-resolution enhancement method based on blind sparse decomposition, in order to improve its resolution of a degraded one. Firstly, sparse decomposition based image super-resolution enhancement model is put forward according to the geometrical invariability of local image structures under different conditions of resolution. Secondly, for reducing the complexity of dictionary learning and enhancing adaptive representation ability of dictionary atoms, the over-complete dictionary is constructed using online learning fashion of the given low resolution image. Thirdly, since the fixed sparsity of the conventional matching pursuit algorithms for sparse decomposition can not fit all types of patches, the approach to sparse decomposition with blind sparsity can achieve relatively higher accurate sparse representation of an image patch. Lastly, atoms of high resolution dictionary and coefficients of representation of the given low-resolution image are synthesized to the desired SR image. Experimental results of the synthetic and real data demonstrate that the suggested framework can eliminate blurring degradation and annoying edge artifacts in the resulting images. The proposed method can be effectively applied to resolution enhancement of the single-frame low-resolution image. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.ioe.ac.cn/handle/181551/7688]  |
| 专题 | 光电技术研究所_光电探测与信号处理研究室（五室） |
| 作者单位 | 中国科学院光电技术研究所 |
| 推荐引用方式 GB/T 7714 | Jinzheng Lu,Qiheng Zhang,Zhiyong Xu,et al. Image super-resolution enhancement based on online learning and blind sparse decomposition[C]. 见:Proc. of SPIE. 2011. |
入库方式： OAI收割
来源：光电技术研究所
浏览0
下载0
收藏0
其他版本
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。