稀疏系数独立可调的单图超分辨率重建

doi:10.11772/j.issn.1001-9081.2016.04.1096

计算机应用 ›› 2016, Vol. 36 ›› Issue (4): 1096-1099.DOI: 10.11772/j.issn.1001-9081.2016.04.1096

稀疏系数独立可调的单图超分辨率重建

倪浩¹, 阮若林², 刘芳华¹, 王建峰³

1. 湖北科技学院电子与信息工程学院, 湖北咸宁 437100;
2. 湖北科技学院生物医学工程学院, 湖北咸宁 437100;
3. 湖北科技学院网络管理中心, 湖北咸宁 437100

收稿日期:2015-07-30 修回日期:2015-10-29 出版日期:2016-04-10 发布日期:2016-04-08
通讯作者: 阮若林
作者简介:倪浩(1981-),男,湖北麻城人,讲师,硕士,主要研究方向:机器学习、计算机视觉; 阮若林(1974-),男,湖北红安人,教授,博士,主要研究方向:视音频编码、图像处理; 刘芳华(1982-),女,湖北孝感人,讲师,硕士,主要研究方向:图像处理; 王建峰(1979-),男,湖北咸宁人,高级工程师,硕士,主要研究方向:计算机网络、图像处理。
基金资助:
国家自然科学基金资助项目(61271256);湖北省高等学校优秀中青年科技创新团队计划项目(T201513);湖北省自然科学基金资助项目(2015CFB452);湖北省教育厅科研计划指导性项目(B2015080)。

Single image super-resolution via independently adjustable sparse coefficients

NI Hao¹, RUAN Ruolin², LIU Fanghua¹, WANG Jianfeng³

1. College of Electronic and Information Engineering, Hubei University of Science and Technology, Xianning Hubei 437100, China;
2. College of Biomedical Engineering, Hubei University of Science and Technology, Xianning Hubei 437100, China;
3. Center of Network Management, Hubei University of Science and Technology, Xianning Hubei 437100, China

Received:2015-07-30 Revised:2015-10-29 Online:2016-04-10 Published:2016-04-08
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61271256), the Team Plan Program of the Outstanding Young Science and Technology Innovation of Colleges and Universities in Hubei Province (T201513), the Natural Science Foundation of Hubei Province (2015CFB452), the Research Project of Education Department in Hubei Province (B2015080).

摘要/Abstract

摘要： 针对基于学习的超分辨率重建图像边缘锐度较好但伪影较明显的问题,提出一种改进的稀疏系数独立可调的超分算法以消除伪影。由于字典训练阶段高分辨率图像和低分辨率图像均已知,认为高维图像空间和低维图像空间对应的稀疏系数不同,故此阶段运用在线字典学习方法分开训练生成较精确的高分字典和低分字典;而在图像重建阶段低分图像已知而高分图像未知,认为两空间的稀疏系数是近似相同的。通过在这两个阶段设置不同的正则化参数,可独立地调整相应的稀疏系数以获得最好的超分效果。实验结果表明,目标高分图像峰值信噪比(PSNR)相比稀疏编码超分方法平均提高了0.45 dB,同时结构相似性(SSIM)指标增加了0.011。超分图像有效地抑制了伪影,并能够较好地恢复图像边缘锐度和纹理细节,提升了超分效果。

关键词: 稀疏系数, 超分辨率重建, 在线字典学习, 单图

Abstract: The recovered image from the example-based super-resolution has sharp edges, but there are obvious artifacts. An improved super-resolution algorithm with independently adjustable sparse coefficients was proposed to eliminate the artifacts. In the dictionary training phase, the sparse coefficients in the high-dimensional space and the low-dimensional space of the image are different because of the known high-resolution training images and low-resolution ones. So the accurate high-resolution dictionary and the low-resolution one were generated separately via online dictionary learning algorithm. In the image reconstruction phase, the sparse coefficients in the two spaces were approximately the same because the input low-resolution image was known but the target high-resolution image was unknown. Different regularization parameters in the two phases were set to tune the corresponding sparse coefficients independently to get the best super-resolution results. According to the experiment results, the Peak Signal-to-Noise Ratio (PSNR) of the proposed method is 0.45 dB higher than that of sparse coding super-resolution in average, while the Structural SIMilarity (SSIM) is also 0.011 higher. The proposed algorithm eliminates the artifacts as well as recovers the edge sharpness and texture details effectively to promote the super-resolution results.

Key words: sparse coefficient, super-resolution reconstruction, online dictionary learning, single image

中图分类号:

TP391.9

倪浩, 阮若林, 刘芳华, 王建峰. 稀疏系数独立可调的单图超分辨率重建[J]. 计算机应用, 2016, 36(4): 1096-1099.

NI Hao, RUAN Ruolin, LIU Fanghua, WANG Jianfeng. Single image super-resolution via independently adjustable sparse coefficients[J]. Journal of Computer Applications, 2016, 36(4): 1096-1099.

参考文献

[1] YANG C Y, MA C, YANG M H, et al. Single-image super-resolution:a benchmark[C]//Proceedings of the 2014 European Conference on Computer Vision. Berlin:Springer, 2014:372-386.
[2] FREEMAN W T, PASZTOR E C, JONES T R. Example-based super-resolution[J]. IEEE Computer Graphics and Applications, 2002, 22(2):56-65.
[3] YANG J C, WRIGHT J, MA Y, et al. Image super-resolution as sparse representation of raw image patches[C]//Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2008:1-8.
[4] YANG J C, WRIGHT J, MA Y. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11):2861-2873.
[5] HE L, QI H U, ZARETZKI R. Beta process joint dictionary learning for coupled feature spaces with application to single image super-resolution[C]//Proceedings of the 2013 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2013:345-352.
[6] GLASNER D, BAGON S, IRANI M. Super-resolution from a single image[C]//Proceedings of the IEEE 2009 International Conference on Computer Vision. Piscataway, NJ:IEEE, 2009:349-356.
[7] 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, LNCS 6920. Berlin:Springer, 2010:711-730.
[8] MAIRAL J, BACH F, PONCE J, et al. Online learning for matrix factorization and sparse coding[J]. Journal of Machine Learning Research, 2010, 11(10):19-60.
[9] YEGANLI F, OZKARAMANLI H. Improved online dictionary learning for sparse signal representation[C]//Proceedings of the 22nd Signal Processing and Communications Applications Conference. Piscataway, NJ:IEEE, 2014:1702-1705.
[10] 杨波, 吴纪桃, 谢晓振.小波域中双稀疏的单幅图像超分辨[J].中国图象图形学报, 2014, 19(11):1570-1576.(YANG B, WU J T, XIE X Z. Single image super-resolution in wavelet domain with double sparse[J]. Journal of Image and Graphics, 2014, 19(11):1570-1576.)
[11] ZHANG K, GAO X, TAO D, et al. Multi-scale dictionary for single image super-resolution[C]//Proceedings of the 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2012:1114-1121.
[12] YANG J, LIN Z, COHEN S. Fast image super-resolution based on in-place example regression[C]//Proceedings of the 2013 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2013:1059-1066.
[13] SADEGHI M, BABAIE-ZADEH M, JUTTEN C. Dictionary learning for sparse representation:a novel approach[J]. IEEE Signal Processing Letters, 2013:20(12):1195-1198.
[14] LEE H, BATTLE A, RAINA R, et al. Efficient sparse coding algorithms[EB/OL].[2015-05-10]. http://machinelearning.wustl.edu/mlpapers/paper_files/NIPS2006_878.pdf.
[15] EFRON B, TIBSHIRANI R. Least angle regression[J]. The Annals of Statistics, 2004, 32(2):2004:407-451.

稀疏系数独立可调的单图超分辨率重建

Single image super-resolution via independently adjustable sparse coefficients

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

[1]	牛康力, 谌雨章, 沈君凤, 曾张帆, 潘永才, 王绎冲. 基于深度学习的双通道夜视图像复原方法[J]. 计算机应用, 2021, 41(6): 1775-1784.
[2]	梁敏, 王昊榕, 张瑶, 李杰. 基于加速残差网络的图像超分辨率重建方法[J]. 计算机应用, 2021, 41(5): 1438-1444.
[3]	杨蒙蒙, 张爱华. 基于灰度共生矩阵和同步正交匹配追踪的分形图像压缩[J]. 计算机应用, 2021, 41(5): 1445-1449.
[4]	段友祥, 张含笑, 孙歧峰, 孙友凯. 基于拉普拉斯金字塔生成对抗网络的图像超分辨率重建算法[J]. 计算机应用, 2021, 41(4): 1020-1026.
[5]	王永金, 左羽, 吴恋, 崔忠伟, 赵晨洁. 基于注意力机制的图像超分辨率重建[J]. 计算机应用, 2021, 41(3): 845-850.
[6]	林静, 黄玉清, 李磊民. 基于球形矩匹配与特征判别的图像超分辨率重建[J]. 计算机应用, 2020, 40(8): 2345-2350.
[7]	胡雪影, 郭海儒, 朱蓉. 基于混合深度卷积网络的图像超分辨率重建[J]. 计算机应用, 2020, 40(7): 2069-2076.
[8]	欧阳宁, 韦羽, 林乐平. 结合感知边缘约束与多尺度融合网络的图像超分辨率重建方法[J]. 计算机应用, 2020, 40(10): 3041-3047.
[9]	姚鲁, 宋慧慧, 张开华. 混合阶通道注意力网络的单图像超分辨率重建[J]. 计算机应用, 2020, 40(10): 3048-3053.
[10]	陈龙彪, 谌雨章, 王晓晨, 邹鹏, 胡学敏. 基于深度学习的水下图像超分辨率重建方法[J]. 计算机应用, 2019, 39(9): 2738-2743.
[11]	刘月峰, 杨涵晰, 蔡爽, 张晨荣. 基于改进卷积神经网络的单幅图像超分辨率重建方法[J]. 计算机应用, 2019, 39(5): 1440-1447.
[12]	许德智, 孙季丰, 罗莎莎. 基于权重量化与信息压缩的车载图像超分辨率重建[J]. 计算机应用, 2019, 39(12): 3644-3649.
[13]	李龙洋, 董一鸿, 施炜杰, 潘剑飞. SQM:基于Spark的大规模单图上的子图匹配算法[J]. 计算机应用, 2019, 39(1): 46-50.
[14]	孙毅堂, 宋慧慧, 张开华, 严飞. 基于极深卷积神经网络的人脸超分辨率重建算法[J]. 计算机应用, 2018, 38(4): 1141-1145.
[15]	彭政, 陈东方, 王晓峰. 正则化超分辨率重建过程的自适应阈值去噪[J]. 计算机应用, 2017, 37(7): 2084-2088.