光电工程, 2015, 42 (8): 79, 网络出版: 2015-09-08  

融合几何变换相似块的序列图像超分辨率重建

Super-resolution Reconstruction of Image Sequences via Fusing Similar Patches with Geometric Transformation
作者单位
1 湖北大学计算机与信息工程学院, 武汉 430062
2 武汉大学电子信息学院, 武汉 430079
摘要
图像内部不同位置或不同图像之间包含有相似的像素或图像分块, 通过对相似块的融合可以完成高分辨率图像的重建。为了充分挖掘图像中潜在的相似信息, 以提高重建质量, 利用图像的几何变换自相似性, 提取图像的邻域 Zernike矩特征进行非局部相似性测度, 提出一种融合几何变换相似信息的联合加权的序列图像超分辨率重建算法。实验结果验证了本文方法的有效性, 与同类方法相比, 本文方法具有更好的重建效果。
Abstract
Similar pixels or image patches exist in different position inside an image or between different images, so that the fusion of similar patches can reconstruct the high resolution image. In order to mine the potential similar information further for the better reconstruction quality, the paper utilizes of the geometry transformation self-similarity of images, by extracting Zernike moments features within the image neighborhood to match and measure the nonlocal similar patches among the images. Then a super-resolution reconstruction algorithm for image sequences is proposed, through the collaborative weighting fusion of similar patches with geometric transformation. The experimental results prove the validity of the proposed method and its superiority in reconstruction effect.
参考文献

[1] Takeda H, Milanfar P, Protter M, et al. Super-resolution without explicit subpixel motion estimation [J]. IEEE Transactions on Image Processing(S1057-7149), 2009, 19(9): 1958-1975.

[2] Danielyan A, Foi A, Katkovnik V, et al. Image and video super-resolution via spatially adaptive block-matching filtering [C]// Proceedings of the International Workshop on Local and Non-Local Approximation in Image Processing, Lausanne, Switzerland, 2008: 1-8.

[3] Protter M, Elad M, Takeda H, et al. Generalizing the non-local-means to super-resolution reconstruction [J]. IEEE Transactions on Image Processing(S1057-7149), 2009, 18(1): 36-51.

[4] Protter M, Elad M. Super resolution with probabilistic motion estimation [J]. IEEE Transactions on Image Processing(S1057-7149), 2009, 18(8): 1899-1904.

[5] YANG Jianchao, Wright J, HUANG Thomas, et al. Image super-resolution as sparse representation [J]. IEEE Transactions on Image Processing(S1057-7149), 2010, 19(11): 2861-2873.

[6] YANG Jianchao, WANG Zhaowen, LIN Zhe, et al. Coupled dictionary training for image super-resolution [J]. IEEE Transactions on Image Processing(S1057-7149), 2012, 21(8): 3467-3478.

[7] 路锦正, 吴斌, 张启衡. 正则化恢复联合稀疏表示的图像超分辨率重构 [J].光电工程, 2013, 40(9): 1-7. LU Jinzheng, WU Bin, ZHANG Qiheng. Image Super-resolution Reconstruction with Regularization Restoration and Sparse Representation [J]. Opto-Electronic Engineering, 2013, 40(9): 1-7.

[8] Peleg T, Elad M. A statistical prediction model based on sparse representations for single image super-resolution [J]. IEEE Transactions on Image Processing(S1057-7149), 2014, 23(6): 2569-2582.

[9] 石大维, 符冉迪, 金炜. 基于耦合过完备字典的红外云图超分辨率方法 [J].光电工程, 2014, 41(4): 69-74. SHI Dawei, FU Randi, JIN Wei.A method of infrared nephogram super-resolution based on coupled over-completed dictionary [J]. Opto-Electronic Engineering, 2014, 41(4): 69-74.

[10] Alexander S, Vrscay E, Tsurumi S.A simple, general model for the affine self-similarity of images [C]// Proceedings of the 5th International Conference on Image Analysis and Recognition, Póvoa de Varzim, Portugal, 2008: 192-203.

[11] Ebrahimi M, Vrscay E.Examining the role of scale in the context of the non-local means filter [C]// Proceedings of the 5th International Conference on Image Analysis and Recognition, Póvoa de Varzim, Portugal, 2008: 170-181.

[12] Lou Y, Favaro P, Soatto S. Nonlocal similarity image filtering [R]. Reports CAM, 2008: 8-26.

[13] Kleinschmidt O, Brox T, Cremers D. Nonlocal texture filtering with efficient tree structures and invariant patch similarity measures [C]// Proceedings of the International Workshop on Local and Non-Local Approximation in Image Processing, Lausanne, Switzerland, 2008: 103-113.

[14] SUN Weifeng, PENG Yuhua, HWANG Wenliang. Modified similarity metric for non-local means algorithm [J]. Electronics Letters(S0013-5194), 2009, 45(25): 1307-1309.

[15] Zimmer S, Didas S, Weickert J. A rotationally invariant block matching strategy improving image denoising with non-local means [C]// Proceedings of the International Workshop on Local and Non-Local Approximation in Image Processing, Lausanne, Switzerland, 2008: 135-142.

[16] JI Zexuan, CHEN Qiang, SUN Quansen, et al. A moment-based nonlocal-means algorithm for image denoising [J]. Information Processing Letters(S0020-0190), 2009, 109(9): 1238-1244.

[17] Chong C, Raveendran P, Mukundan R. A comparative analysis of algorithm for fast computation of Zernike moments [J]. Pattern Recognition(S0031-3203), 2003, 36(3): 731-742.

[18] YE Bin, PENG Jiaxiong. Invariance analysis of improved Zernike moments [J]. Journal of Optics A: Pure and Applied Optics(S1464-4258), 2002, l(4): 606-614.

[19] WANG Zhou, Bovik A, Sheikh H, et al. Image quality assessment: from error visibility to structural similarity [J]. IEEE Transactions on Image Processing(S1057-7149), 2004, 13(4): 1-14.

郭琳, 叶波, 陈庆虎, 陈汉中. 融合几何变换相似块的序列图像超分辨率重建[J]. 光电工程, 2015, 42(8): 79. GUO Lin, YE Bo, CHEN Qinghu, CHEN Hanzhong. Super-resolution Reconstruction of Image Sequences via Fusing Similar Patches with Geometric Transformation[J]. Opto-Electronic Engineering, 2015, 42(8): 79.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!