基于自适应多字典学习的单幅图像超分辨率算法

doi:10.3969/j.issn.0372-2112.2015.02.001

电子学报 ›› 2015, Vol. 43 ›› Issue (2): 209-216.DOI: 10.3969/j.issn.0372-2112.2015.02.001

• 学术论文 • 下一篇

基于自适应多字典学习的单幅图像超分辨率算法

潘宗序¹, 禹晶¹, 肖创柏², 孙卫东¹

1. 清华大学电子工程系, 北京 100084;
2. 北京工业大学计算机学院, 北京 100124

收稿日期:2013-06-08 修回日期:2014-06-09 出版日期:2015-02-25
- 作者简介:
- 潘宗序 男,1986年生于黑龙江省.2010年获哈尔滨工业大学电子与信息工程学院学士学位.现为清华大学电子工程系博士研究生.主要研究方向为图像处理,模式识别,压缩感知与稀疏表示,空间信息处理与应用. Email:panzxtsinghua@163.com;禹晶 女,1981年生于陕西省.2011年获清华大学电子工程系博士学位.现为清华大学电子工程系博士后.主要研究方向为图像处理和模式识别;肖创柏 男,1962年生于湖南省.1995年毕业于清华大学,获博士学位.现为北京工业大学计算机学院教授.主要研究方向为数字信号处理,音视频信号处理与网络通信,模式识别等;孙卫东 男,1960年生于山东省.1988年获日本东京大学博士学位.现为清华大学电子工程系教授.主要研究方向为图像处理,模式识别,空间信息处理与应用等.
- 基金资助:
- 国家科技支撑计划 (No.2012BAH31B01); 国家自然科学基金 (No.61171117); 北京市教育委员会科技计划重点项目 (No.KZ201310028035)

Single Image Super Resolution Based on Adaptive Multi-Dictionary Learning

PAN Zong-xu¹, YU Jing¹, XIAO Chuang-bai², SUN Wei-dong¹

1. Department of Electronic Engineering, Tsinghua University, Beijing 100084, China;
2. College of Computer Science and Technology, Beijing University of Technology, Beijing 100124, China

Received:2013-06-08 Revised:2014-06-09 Online:2015-02-25 Published:2015-02-25
- Supported by:
- National Key Technology Research and Development Program of the Ministry of Science and Technology (No.2012BAH31B01); National Natural Science Foundation of China (No.61171117); Key Program of Science and Technology Planning Project of Beijing Municipality Education Commission (No.KZ201310028035)

摘要/Abstract

摘要：

自适应字典学习利用图像结构自相似性,将图像自身作为训练样本,通过字典学习使图像中的相似块在字典下具有稀疏表示形式.本文将全局字典学习中利用图像库获取附加信息的思想融入到自适应字典学习的过程中,提出了一种基于自适应多字典学习的单幅图像超分辨率算法,从低分辨率图像自身与图像库同时获取附加信息.该算法对低分辨率图像金字塔结构中的图像块进行聚类,在聚类结果的引导下将图像库中的图像块进行分类,利用各类中的样本分别构建针对各类的多个字典,从而确定表达重建图像块的最优字典.实验表明,与ScSR、SISR、NLIBP、CSSS以及mSSIM等算法相比,本文算法具有更好的超分重建效果.

关键词: 超分辨率, 稀疏表示, 自适应字典学习, 全局字典学习

Abstract:

Adaptive dictionary learning uses the low resolution image itself as training samples to make the similar patches have sparse representation over the learned dictionary,so that extra information can be exploited from structural self-similarity by dictionary learning.In this paper,we propose a single image super resolution method based on adaptive multi-dictionary learning.To exploit extra information from both the low resolution image itself,and the image database,the proposed method incorporates the idea of global dictionary learning that the image database can be used to obtain extra information into the process of adaptive dictionary learning.In the proposed method,all patches in the image pyramid of the low resolution image are clustered into several groups,then each patch satisfying a certain condition in the database is classified into one of these groups with the supervision of the clustering results,and multi-dictionary learning is used to learn corresponding dictionaries for different groups.Experimental results demonstrate that our method achieves better result compared with ScSR,SISR,NLIBP,CSSS and mSSIM methods.

Key words: super resolution, sparse representation, adaptive dictionary learning, global dictionary learning

中图分类号:

TN911.73

潘宗序, 禹晶, 肖创柏, 等. 基于自适应多字典学习的单幅图像超分辨率算法[J]. 电子学报, 2015, 43(2): 209-216.

PAN Zong-xu, YU Jing, XIAO Chuang-bai, et al. Single Image Super Resolution Based on Adaptive Multi-Dictionary Learning[J]. Acta Electronica Sinica, 2015, 43(2): 209-216.

参考文献

[1] 邵文泽,韦志辉.基于各向异性MRF建模的多帧图像变分超分辨率重建[J].电子学报,2009,37(6):1256-1263. Shao Wenze,Wei Zhihui.Multi-frame super-resolution reconstruction based on anisotropic Markov random field modeling[J].Acta Electronica Sinica,2009,37(6):1256-1263.(in Chinese)
[2] 宋锐,吴成柯,封颖,张云锋.一种新的基于MAP的纹理自适应超分辨率图像复原算法[J].电子学报,2009,37(5):1124-1129. Song Rui,Wu Chengke,Feng Ying,Zhang Yunfeng.A new MAP based texture adaptive super-resolution image reconstruction algorithm[J].Acta Electronica Sinica,2009,37(5):1124-1129.(in Chinese)
[3] Yang J,Wright J,Huang T S,Ma Y.Image super-resolution via sparse representation[J].IEEE Transactions on Image Processing,2010,19(11):2861-2873.
[4] Protter M,Elad M,Takeda H,Milanfar P.Generalizing the nonlocal-means to super-resolution reconstruction[J].IEEE Transactions on Image Processing,2009,18(1):36-51.
[5] Dong W,Zhang L,Shi G,Wu X.Nonlocal back-projection for adaptive image enlargement[A].Proceedings of the 2009 IEEE International Conference on Image Processing[C].Cairo,Egypt:IEEE Computer Society,2009.349-352.
[6] Glasner D,Bagon S,Irani M.Super-resolution from a single image[A].Proceedings of the 12th International Conference on Computer Vision[C].Kyoto,Japan:IEEE Inc,2009.349-356.
[7] Pan Z,Yu J,Huang H,Hu S,Zhang A,Ma H,Sun W.Super-resolution based on compressive sensing and structural self-similarity for remote sensing images[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(9):4864-4876.
[8] 潘宗序,禹晶,胡少兴,孙卫东.基于多尺度结构自相似性的单幅图像超分辨率算法[J].自动化学报,2014,40(4):594-603. Pan Zongxu,Yu Jing,Hu Shaoxing,Sun Weidong.Single image super resolution based on multi-scale structural self-similarity[J].Acta Automatica Sinica,2014,40(4):594-603.(in Chinese)
[9] Engan K,Aase S O,Husoy J H.Method of optimal directions for frame design[A].Proceedings of the 1999 IEEE International Conference on Acoustics,Speech,and Signal Processing[C].Phoenix,AZ,USA:IEEE,1999.2443-2446.
[10] Aharon M,Elad M,Bruckstein A.K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[11] Elad M,Aharon M.Image denoising via sparse and redundant representations over learned dictionaries[J].IEEE Transactions on Image Processing,2006,15(12):3736-3745.
[12] Gribonval R,Nielsen M.Sparse representations in unions of bases[J].IEEE Transactions on Information Theory,2003,49(12):3320-3325.
[13] Freeman W T,Jones T R,Pasztor E C.Example-based super-resolution[J].IEEE Computer Graphics and Applications,2002,22(2):56-65.
[14] Daubechies I,Defrise M,De Mol C.An iterative thresholding algorithm for linear inverse problems with a sparsity constraint[J].Communications on Pure and Applied Mathematics,2004,57(11):1413-1457.

[1]	刘杰, 葛一凡, 田明. 文物图像的超分辨率重建算法研究[J]. 电子学报, 2023, 51(1): 139-145.
[2]	李滔, 董秀成, 林宏伟. 基于深监督跨尺度注意力网络的深度图像超分辨率重建[J]. 电子学报, 2023, 51(1): 128-138.
[3]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[4]	王相海, 赵晓阳, 王鑫莹, 赵克云, 宋传鸣. 非抽取小波边缘学习深度残差网络的单幅图像超分辨率重建[J]. 电子学报, 2022, 50(7): 1753-1765.
[5]	周登文, 李文斌, 李金新, 黄志勇. 一种轻量级的多尺度通道注意图像超分辨率重建网络[J]. 电子学报, 2022, 50(10): 2336-2346.
[6]	田典, 余宁梅, 周广霖, 李娜. 双线阵无透镜超分辨率扫描成像方法研究[J]. 电子学报, 2022, 50(10): 2503-2516.
[7]	冯西安, 寇思玮, 谭伟杰, 毕杨. 水声信号处理中的稀疏表示理论及应用[J]. 电子学报, 2021, 49(9): 1840-1851.
[8]	禤韵怡, 杨春玲. 基于帧间组稀疏的两阶段递归增强视频压缩感知重构网络[J]. 电子学报, 2021, 49(3): 435-442.
[9]	夏楠, 高紫俊, 李博, 王珏. 一种基于循环稀疏表示的同频带干扰抑制及发射源定位方法[J]. 电子学报, 2021, 49(1): 8-13.
[10]	唐艳秋, 潘泓, 朱亚平, 李新德. 图像超分辨率重建研究综述[J]. 电子学报, 2020, 48(7): 1407-1420.
[11]	郑学炜, 杨春玲, 禤韵怡. CVS中基于视频运动特征的多假设-双稀疏重构算法[J]. 电子学报, 2020, 48(2): 249-257.
[12]	脱婷, 马慧芳, 李志欣, 赵卫中. 熵权约束稀疏表示的短文本分类算法[J]. 电子学报, 2020, 48(11): 2131-2137.
[13]	周浦城, 张杰, 薛模根, 尹璋堃. 基于卷积分析稀疏表示和相位一致性的低照度图像增强[J]. 电子学报, 2020, 48(1): 180-188.
[14]	田文飚, 芮国胜, 董道广, 康健. 基于盲自适应KLT的蒸发波导压缩感知方法[J]. 电子学报, 2018, 46(9): 2068-2074.
[15]	王相海, 赵晓阳, 毕晓昀, 陶兢喆. 小波域多角度轮廓模板变分模型的单幅图像超分辨率重建[J]. 电子学报, 2018, 46(9): 2256-2262.

基于自适应多字典学习的单幅图像超分辨率算法

Single Image Super Resolution Based on Adaptive Multi-Dictionary Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics