基于自相似性和稀疏表示的图像超分辨率重建

蒋建国; 陈亚运; 齐美彬; 王超

doi:doi:10.3969/j.issn.1003-501x.2015.12.013

光电工程, 2015, 42 (12): 0074, 网络出版: 2016-01-20

基于自相似性和稀疏表示的图像超分辨率重建

Image Super-resolution Reconstruction Based on Self-similarity and Sparse Representation

论文大纲

蒋建国 ^*陈亚运齐美彬王超

作者单位

合肥工业大学计算机与信息学院，合肥 230009

超分辨率自相似性稀疏表示稀疏K-SVD 非局部均值 super-resolution self-similarity sparse representation sparse K-SVD non-local means

摘要

图像超分辨率重建技术在提升图像质量，改善图像视觉效果等方面有着重要意义。为了充分利用图像自身蕴含的信息，本文提出一种基于自相似性和稀疏表示的单幅图像超分辨率重建算法。针对图像中存在的相同尺度和不同尺度的相似结构，算法联合稀疏K-SVD 字典学习方法和非局部均值方法将蕴含在其中的有效信息以正则项的形式加入到最大后验概率估计框架中，然后，采用梯度下降法求解算法构建的目标函数，重建出高分辨率图像。实验表明，与经典的算法相比，本文算法在视觉效果和评价指标上都有一定的提高。

Abstract

Super-resolution reconstruction plays an important role in adding the image details and improving the visual perception. In order to effectively exploit the effective information hidden in the image itself, we proposed a single image super-resolution reconstruction method based on self-similarity and sparse representation. The method combines sparse K-SVD dictionary learning and nonlocal means，which are used to add the effective information hidden in the same scale and across different scales structural self-similarity into the maximum a posteriori probability estimation framework by two different regularization terms. Then, a local optimal solution is obtained by using the gradient descent algorithm. The experimental results show that our method has a better improvement both visually and quantitatively.

参考文献

[1] Park S C，Park M K，Kang M G. Super-resolution image reconstruction：a technical overview[J]. IEEE Signal Processing Magazine(S1053-5888)，2003，20(3)：21-36.

[2] LI Xin，Orchard M T. New edge-directed interpolation[J]. IEEE Transactions on Image Processing(S1057-7149)，2001， 10(10)：1521-1527.

[3] LI Xin，Nguyen T Q. Markov random field model-based edge-directed image interpolation[J]. IEEE Transactions on Image Processing(S1057-7149)，2008，17(7)：1121-1128.

[4] Schultz R R，Stevenson R L. A Bayesian approach to image expansion for improved definition[J]. IEEE Transactions on Image Processing(S1057-7149)，1994，3(3)：233-242.

[5] Irani M，Peleg S. Improving resolution by image registration[J]. CVGIP：Graphical Models and Image Processing (S1049-9652)，1991，53(3)：231-239.

[6] Marquina A，Osher S J. Image super-resolution by TV-regularization and Bregman iteration[J]. Journal of Scientific Computing(S1573-7691)，2008，37(3)：367-382.

[7] LI Lin，XIE Yuan，HU Wenrui，et al. Single image super-resolution using combined total variation regularization by split Bregman Iteration[J]. Neurocomputing(S0925-2312)，2014，142：551-560.

[8] SUN Jian，XU Zongben，Shum H Y. Image super-resolution using gradient profile prior [C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition，Anchorage，AK，June 23-28，2008：1-8.

[9] Mairal J，Bach F，Ponce J，et al. Non-local sparse models for image restoration [C]// Proceedings of the 12th IEEE International Conference on Computer Vision，Kyoto，Japan，Sept 29-Oct 2，2009：2272-2279.

[10] YANG Jianchao，Wright J，Huang T S，et al. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing(S1057-7149)，2010，19(11)：2861-2873.

[11] Zeyde R，Elad M，Protter M. On Single Image Scale-up using Sparse Representations [C]// Proceedings of the 7th International Conference on Curves and Surfaces，Avignon，France，June 24-30，2012，6920：711-730.

[12] Glasner D，Bagon S，Irani M. Super-resolution from a single image [C]// Proceedings of the 12th IEEE International Conference on Computer Vision，Kyoto，Japan，Sept 29-Oct 2，2009：349-356.

[13] ZHANG Kaibing，GAO Xinbo，TAO Dacheng，et al. Single image super-resolution with non-local means and steering kernel regression[J]. IEEE Transactions on Image Processing(S1057-7149)，2012，21(11)：4544-4556.

[14] DONG Weisheng，ZHANG Lei，SHI Guangming，et al. Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization[J]. IEEE Transactions on Image Processing(S1057-7149)，2011，20(7)：1838-1857.

[15] HE Li，QI Hairong，Zaretzki R. Beta process joint dictionary learning for coupled feature spaces with application to single image super-resolution [C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition，Portland，OR，USA， June 23-28，2013：345-352.

[16] ZHU Qidan，SUN Lei，CAI Chengtao. Non-local neighbor embedding for image super-resolution through FoE features[J]. Neurocomputing(S0925-2312)，2014，141：211-222.

[17] Rubinstein R，Zibulevsky M，Elad M. Double sparsity：Learning sparse dictionaries for sparse signal approximation[J]. IEEE Transactions on Signal Processing(S1057-7149)，2010，58(3)：1553-1564.

[18] YU Jifei，GAO Xinbo，TAO Dacheng，et al. A unified learning framework for single image super-resolution[J]. IEEE Transactions on Neural Networks and Learning Systems(S2162-237X)，2014，25(4)：780-792.

蒋建国, 陈亚运, 齐美彬, 王超. 基于自相似性和稀疏表示的图像超分辨率重建[J]. 光电工程, 2015, 42(12): 0074. JIANG Jianguo, CHEN Yayun, QI Meibin, WANG Chao. Image Super-resolution Reconstruction Based on Self-similarity and Sparse Representation[J]. Opto-Electronic Engineering, 2015, 42(12): 0074.

基于自相似性和稀疏表示的图像超分辨率重建

关于本站 Cookie 的使用提示

全站搜索

基于自相似性和稀疏表示的图像超分辨率重建

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索