|
|
- 2018
利用在线字典学习实现图像超分辨率重建的算法
|
Abstract:
图像超分辨率重建是通过对单张或多张具有互补信息的低分辨率图像进行处理，重建一张高分辨率图像的技术。在单张图像的超分辨率重建中，基于稀疏表示的方法取得了很好的效果，得到了广泛的应用。一张图像中不同区域的图像块的内容一般会有显著变化。而基于稀疏表示的超分辨率重建算法多采用固定的字典，无法适应每一个图像块的重建需求。提出了一种结合外部数据和输入图像自身信息进行超分辨率重建的方法，通过搜索待处理图像块的非局部自相似块，结合在线字典学习方法对字典进行更新，从而保证更新后的字典能够匹配待处理的图像块。采用包括遥感图像在内的5张图像进行实验，并与4种经典的超分辨率重建算法进行比较，实验结果表明，此算法在主观评价和客观评价方面都有更好的表现
| [1] | Yang J, Wright J, Huang T, et al. Image Super-resolution via Sparse Representation[J]. <em>IEEE Trans Image Process</em>, 2010, 19(11):2861-2873 |
| [2] | Freeman W T, Jones T R, Pasztor E C. Example-Based Super-resolution[J]. <em>IEEE Computer Graphics & Applications</em>, 2002, 22(2):56-65 |
| [3] | Efron B, Hastie T, Johnstone L, et al. Least Angle Regression[J]. <em>Annals of Statistics</em>, 2004, 32(2):494-499 |
| [4] | Zhang L, Zhang L, Mou X, et al. FSIM:A Feature Similarity Index for Image Quality Assessment[J]. <em>IEEE Trans Image Process, </em>2011, 20(8):2378-2386 |
| [5] | Marquina A, Osher S J. Image Super-Resolution by TV-Regularization and Bregman Iteration[J]. <em>Journal of Scientific Computing</em>, 2008, 37(3):367-382 |
| [6] | Sun J, Sun J, Xu Z, et al. Image Super-resolution using Gradient Profile Prior[C]. The IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Anchorage, USA, 2008 |
| [7] | Lan Chengdong, Chen Liang, Lu Tao. Face Super-resolution Using Sparse Representation with Position Weights[J]. <em>Geomatics and Information Science of Wuhan University</em>, 2013, 38(1):27-30(兰诚栋,陈亮,卢涛.利用位置权重系数表示的人脸超分辨率算法[J].武汉大学学报·信息科学版,2013,38(1):27-30) |
| [8] | Dong W, Zhang L, Shi G, et al. Image Deblurring and Super-resolution by Adaptive Sparse Domain Selection and Adaptive Regularization[J]. <em>IEEE Trans Image Process</em>, 2011, 20(7):1838-1857 |
| [9] | Donoho D L. For Most Large Underdetermined Systems of Equations, the Minimal 11-norm Near-Solution Approximates the Sparsest Near-solution[J]. Comm. Pure Appl. Math., 2006, 59(7):907-934 |
| [10] | Zhang J, Zhao C, Xiong R, et al. Image Super-resolution via Dual-dictionary Learning and Sparse Representation[C]. IEEE International Symposium on Circuits and Systems, COEX, Seoul, Korea, 2012 |
| [11] | Mairal J, Bach F, Ponce J, et al. Online Learning for Matrix Factorization and Sparse Coding[J].<em>Journal of Machine Learning Research</em>, 2010, 11(1):19-60 |
| [12] | Pablo A, Michael M, Charless F, et al. Contour Detection and Hierarchical Image Segmentation[J]. <em>IEEE Transactions Pattern Analysis and Machine Intelligence</em>, 2011, 33(5):898-916 |
| [13] | Zhang Liangpei, Shen Huanfeng, Zhang Hongyan. Image Super-resolution Reconstruction[M]. <em>Science Press</em>, 2012(张良培,沈焕锋,张洪艳.图像超分辨率重建[M]. 北京:科学出版社,2012) |
| [14] | Liu Shuai, Zhu Yajie, Xue Lei. Remote Sensing Image Super-resolution Method Using Sparse Representation and Classified Texture Patches[J].<em>Geomatics and Information Science of Wuhan University</em>, 2015, 40(5):578-582(刘帅,朱亚杰,薛磊. 一种结合稀疏表示和纹理分块的遥感影像超分辨率方法[J].武汉大学学报·信息科学版,2015,40(5):578-582) |
| [15] | Dai S, Han M, Xu W, et al. Soft Cuts:A Soft Edge Smoothness Prior for Color Image Super-resolution[J]. <em>IEEE Trans Image Process</em>, 2009, 18(5):969-981 |
| [16] | Glasner D, Bagon S, Irani M. Super-Resolution From a Single Image[C]. The IEEE International Conference on Computer Vision, Kyoto, Japan, 2009 |
