增强的单幅图像自学习超分辨方法

doi:10.11772/j.issn.1001-9081.2017.09.2636

计算机应用 ›› 2017, Vol. 37 ›› Issue (9): 2636-2642.DOI: 10.11772/j.issn.1001-9081.2017.09.2636

• 计算机视觉与虚拟现实 • 上一篇下一篇

增强的单幅图像自学习超分辨方法

黄凤¹, 王晓明^1,2

1. 西华大学计算机与软件工程学院, 成都 610039;
2. 西华大学机器人研究中心, 成都 610039

收稿日期:2017-03-30 修回日期:2017-06-07 出版日期:2017-09-10 发布日期:2017-09-13
通讯作者: 王晓明,wxmwm@aliyun.com
作者简介:黄凤(1993-),女,四川南部人,硕士研究生,主要研究方向:图像超分辨率重建;王晓明(1977-),男,四川简阳人,副教授,博士,主要研究方向:模式识别、机器学习、图像处理、计算机视觉。
基金资助:
国家自然科学基金资助项目（61532009）；教育部春晖计划项目（Z2015102）；四川省教育厅自然科学重点项目（11ZA004）。

Enhanced self-learning super-resolution approach for single image

HUANG Feng¹, WANG Xiaoming^1,2

1. School of Computer and Software Engineering, Xihua University, Chengdu Sichuan 610039, China;
2. Robotics Research Center of Xihua University, Chengdu Sichuan 610039, China

Received:2017-03-30 Revised:2017-06-07 Online:2017-09-10 Published:2017-09-13
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61532009), the Chunhui Program of Ministry of Education (Z2015102), the Key Scientific Research Project of Sichuan Provincial Department of Education (11ZA004).

摘要/Abstract

摘要： 针对图像超分辨率方法构建图像块的稀疏表示（SR）系数存在的主要问题，利用加权思想提出一种增强的单幅图像自学习超分辨方法。首先，通过自学习建立高低分辨率图像金字塔；然后，分别提取低分辨率图像的图像块特征和对应高分辨率图像块的中心像素，并给图像块中不同像素点赋予不同的权重，强调中心像素点在构建图像块稀疏系数时的作用；最后，结合SR理论和支持向量回归（SVR）技术建立超分辨率图像重建模型。实验结果表明，与单幅图像自学习超分辨率方法（SLSR）相比，所提方法的峰值信噪比（PSNR）平均提高了0.39 dB，无参考图像质量评价标准（BRISQUE）分数平均降低了9.7。从主观视角和客观数值证明了所提超分辨率方法更有效。

关键词: 数字图像处理, 单幅图像超分辨率, 稀疏表达, 支持向量回归, 权重系数

Abstract: Aiming at the main problem of the Sparse Representation (SR) coefficients of the image blocks in image super-resolution method, an enhanced self-learning super-resolution approach for single image was proposed by using the weighting idea. Firstly, the pyramid of high and low resolution images was established by self-learning. Then, the image block feature of low-resolution images and the central pixels of the corresponding high-resolution image blocks were extracted respectively. The role of the center pixel in constructing the image block sparse coefficient was emphasized by giving different weights of different pixels in the image blocks. Finally, the combination of SR theory and Support Vector Regression (SVR) technique was used to build the super-resolution image reconstruction model. The experimental results show that compared with the Self-Learning Super-Resolution method for single image (SLSR), the Peak Signal-to-Noise Ratio (PSNR) of the proposed method is increased by an average of 0.39 dB, the BRISQUE (Blind/Reference-less Image Spatial Quality Evaluator) score of no-reference image quality evaluation criteria is reduced by an average of 9.7. From the subjective perspective and objective values, it is proved that the proposed super resolution method is more effective.

Key words: digital image processing, single image super-resolution, Sparse Representation (SR), Support Vector Regression (SVR), weight coefficient

中图分类号:

TP391.41

黄凤, 王晓明. 增强的单幅图像自学习超分辨方法[J]. 计算机应用, 2017, 37(9): 2636-2642.

HUANG Feng, WANG Xiaoming. Enhanced self-learning super-resolution approach for single image[J]. Journal of Computer Applications, 2017, 37(9): 2636-2642.

参考文献

[1] 杨欣.图像超分辨率技术原理及应用[M].北京:国防工业出版社,2013:2-9,93.(YANG X. Image Super Resolution Technology Principle and Application[M]. Beijing:National Defense Industry Press, 2013:2-9,93.)
[2] 赵伟.基于多幅低分辨率图像的超分辨率图像重建[D].南京:东南大学,2011:12-17. (ZHAO W. Super-resolution image reconstruction based on multiple low resolution images[D]. Nanjing:Southeast University, 2011:12-17.)
[3] 王宇,吴炜,严斌宇,等.基于SVR的人脸图像超分辨率复原算法[J].四川大学学报(自然科学版),2013,50(4):728-736.(WANG Y, WU W, YAN B Y, et al. Face hallucination based on SVR[J].Journal of Sichuan University (Natural Science Edition), 2013, 50(4):728-736.)
[4] XU J, DENG C, GAO X, et al. Image super-resolution using multi-layer support vector regression[C]//Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ:IEEE, 2014:5799-5803.
[5] AN L, BHANU B. Improved image super-resolution by support vector regression[C]//Proceedings of the 2011 International Joint Conference on Neural Networks. Piscataway, NJ:IEEE, 2011:696-700.
[6] YANG J, WRIGHT J, HUANG T S, et al. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11):2861-2873.
[7] YANG M C, WANG Y C F. A self-learning approach to single image super-resolution[J]. IEEE Transactions on Multimedia, 2013, 15(3):498-508.
[8] YANG M C, CHU C T, WANG Y C F. Learning sparse image representation with support vector regression for single-image super-resolution[C]//Proceedings of the 201017th IEEE International Conference on Image Processing. Piscataway, NJ:IEEE, 2010:1973-1976.
[9] 范九伦,史香晔,徐健,等.多级字典学习的图像超分辨率算法[J].西安邮电大学学报,2016,21(3):32-37.(FAN J L, SHI X Y, XU J, et al. Image super-resolution algorithm based on multi-level dictionaries learning[J]. Journal of Xi'an University of Posts and Telecommunications, 2016, 21(3):32-37.)
[10] 邱大伟,刘彦隆.改进的稀疏表示图像超分辨率复原算法[J].电视技术,2016,40(1):135-140. (QIU D W, LIU Y L. Improved image super-resolution via sparse representation[J]. Video Engineering, 2016, 40(1):135-140.)
[11] 李欣,崔子冠,孙林慧,等.基于局部回归模型的图像超分辨率重建[J].计算机应用,2016,36(6):1654-1658. (LI X, CUI Z G, SUN L H, et al. Image super-resolution reconstruction based on local regression model[J]. Journal of Computer Applications, 2016, 36(6):1654-1658.)
[12] 王宏,卢芳芳,李建武.结合支持向量回归和图像自相似的单幅图像超分辨率算法[J].中国图象图形学报,2016,21(8):986-992.(WANG H, LU F F, LI J W. Single image super-resolution via support vector regression and image self-similarity[J]. Journal of Image and Graphics, 2016, 21(8):986-992.)
[13] WANG Z, LIU D, YANG J, et al. Deep networks for image super-resolution with sparse prior[EB/OL].[2016-12-07]. http://pdfs.semanticscholar.org/27fc/88ebb3e325a062a6ff48a7a76611af1ecd5a.pdf.
[14] MALLAT S. A wavelet tour of signal processing:the sparse way[EB/OL].[2016-12-07]. http://www.gbv.de/dms/ilmenau/toc/579284751.PDF.
[15] BASAK D, PAL S, PATRANABIS D C. Support vector regression[J]. Neural Information Processing Letters and Reviews, 2007, 11(10):203-224.
[16] MAIRAL J, BACH F, PONCE J, et al. Online learning for matrix factorization and sparse coding[J]. Journal of Machine Learning Research, 2010, 11(1):19-60.
[17] MAIRAL J, BACH F, PONCE J, et al. Online dictionary learning for sparse coding[C]//Proceedings of the 26th Annual International Conference on Machine Learning. New York:ACM, 2009:689-696.
[18] EFRON B, HASTIE T, JOHNSTONE I, et al. Least angle regression (with discussion)[EB/OL].[2017-01-06]. https://web.stanford.edu/~hastie/Papers/LARS/LeastAngle_2002.pdf.
[19] University of Southern California. The USC-SIPI image database[DB/OL].[2016-08-20]. http://sipi.usc.edu/database/.
[20] MOORTHY A K, BOVIK A C. A two-step framework for constructing blind image quality indices[J]. IEEE Signal Processing Letters, 2010, 17(5):513-516.
[21] MITTAL A, MOORTHY A K, BOVIK A C. No-reference image quality assessment in the spatial domain[J]. IEEE Transactions on Image Processing, 2012, 21(12):4695-4708.
[22] MAIRAL J. SPAMS:a sparse modeling software, v2.5[EB/OL].[2016-10-23]. http://spams-devel.gforge.inria.fr/downloads.html.
[23] CHANG C, LIN C J. LIBSVM:a library for support vector machines[EB/OL].[2016-10-18]. http://www.csie.ntu.edu.tw/~cjlin/libsvm.

增强的单幅图像自学习超分辨方法

Enhanced self-learning super-resolution approach for single image

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]	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.
[2]	杨震, 王红军. 基于Adaboost-Markov模型的移动用户位置预测方法[J]. 计算机应用, 2019, 39(3): 675-680.
[3]	金滔, 董秀成, 李亦宁, 任磊, 范佩佩. 改进的粒子群优化算法优化分数阶PID控制器参数[J]. 计算机应用, 2019, 39(3): 796-801.
[4]	严德赛, 曾诚. 基于数字图像处理的眼球控制精度提高方法[J]. 计算机应用, 2018, 38(10): 3013-3016.
[5]	覃雄派, 陈跃国, 王邦国. 大数据分析的应用案例——投资模型的稳健性[J]. 计算机应用, 2017, 37(3): 660-667.
[6]	管非凡, 郁梅, 宋洋, 邵华, 蒋刚毅. 高动态范围图像客观质量评价方法[J]. 计算机应用, 2017, 37(3): 695-698.
[7]	王定成, 赵友志, 陈北京, 陆一祎. 多输出数据依赖核支持向量回归快速学习算法[J]. 计算机应用, 2017, 37(3): 746-749.
[8]	王春荣, 夏尔冬, 吴龙, 刘建军, 熊昌炯. 基于改进支持向量回归算法的移动机器人定位[J]. 计算机应用, 2016, 36(9): 2545-2549.
[9]	王坤, 员晓阳, 王力. 基于改进模糊支持向量回归模型的机场能源需求预测[J]. 计算机应用, 2016, 36(5): 1458-1463.
[10]	马允, 王晓东, 章联军. 基于空域自然场景统计的无参考立体图像质量评价模型[J]. 计算机应用, 2016, 36(3): 783-788.
[11]	赵小乐, 吴亚东, 田金沙, 张红英. 统一最小二乘规则的单幅图像超分辨算法[J]. 计算机应用, 2016, 36(3): 800-805.
[12]	卢涛, 杨威, 万永静. 基于图像超分辨极限学习机的极低分辨率人脸识别[J]. 计算机应用, 2016, 36(2): 580-585.
[13]	李俊山, 仝奇, 叶霞, 许元. 基于相空间重构的自适应残差修正支持向量回归预测算法[J]. 计算机应用, 2016, 36(11): 3229-3233.
[14]	张欣, 胡新韬, 郭雷. 基于动态功能连接的运动任务大脑状态表达[J]. 计算机应用, 2015, 35(7): 1933-1938.
[15]	游子毅, 陈世国, 王义. 基于ε-支持向量回归理论的区域交通信号智能控制[J]. 计算机应用, 2015, 35(5): 1361-1366.