基于自然图像块相似性和稀疏先验性的图像复原

doi:10.11772/j.issn.1001-9081.2017.08.2319

计算机应用 ›› 2017, Vol. 37 ›› Issue (8): 2319-2323.DOI: 10.11772/j.issn.1001-9081.2017.08.2319

• 计算机视觉与虚拟现实 • 上一篇下一篇

基于自然图像块相似性和稀疏先验性的图像复原

李俊山^1,2, 杨亚威³, 朱子江¹, 张姣²

1. 广东外语外贸大学南国商学院信息科学技术学院, 广州 510545;
2. 火箭军工程大学信息工程系, 西安 710025;
3. 96215部队, 广西柳州 545616

收稿日期:2016-12-23 修回日期:2017-02-11 出版日期:2017-08-10 发布日期:2017-08-12
通讯作者: 李俊山
作者简介:李俊山(1956-),男,陕西白水人,教授,博士,CCF会员,主要研究方向:图像处理、计算机视觉、图像复原;杨亚威(1986-),男,湖南民权人,工程师,博士,主要研究方向:红外图像处理、目标识别、图像复原;朱子江(1977-),男,湖南娄底人,副教授,硕士,主要研究方向:图像处理、软件工程;张姣(1988-),女,陕西汉中人,博士研究生,主要研究方向:图像复原、目标识别。
基金资助:
国家自然科学基金资助项目（61175120）。

Image restoration based on natural patch likelihood and sparse prior

LI Junshan^1,2, YANG Yawei³, ZHU Zijiang¹, ZHANG Jiao²

1. Institute of Information Science and Technology, South China Business College, Guangdong University of Foreign Studies, Guangzhou Guangdong 510545, China;
2. Department of Information Engineering, Rocket Force University of Engineering, Xi'an Shaanxi 710025, China;
3. 96215 Unit, Liuzhou Guangxi 545616, China

Received:2016-12-23 Revised:2017-02-11 Online:2017-08-10 Published:2017-08-12
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61175120).

摘要/Abstract

摘要： 针对物体成像过程受光学系统散焦、运动、大气扰动及光电噪声等因素影响，导致光学系统获取的图像存在噪声、模糊、畸变等降质问题，对基于自然图像块相似性和自然图像稀疏先验信息的图像复原方法进行研究，提出一种泛化的基于图像块相似性和自然图像稀疏先验的图像复原框架。首先，在研究自然图像稀疏先验模型的基础上比较了几种图像块的相似性模型，比较结果表明在图像复原中利用图像块的高相似性先验条件模型能够提升图像复原的性能；接着，构建和优化了基于图像块的期望log相似性模型，减少了运行时间，简化了学习过程；最后，通过构建一种近似的最大后验估计（MAP）算法，最终实现了基于优化的期望块log相似性和混合高斯模型（GMM）的图像复原。仿真实验结果表明，所提方法能够很好地复原包含有各种模糊和加性噪声的退化图像，所得图像的峰值信噪比（PSNR）和结构相似度（SSIM）都优于当前技术条件下的其他稀疏先验复原方法，并具有更好的视觉效果。

关键词: 图像复原, 图像块相似性, 稀疏先验性, 期望块log相似性, 高斯混合模型

Abstract: Concerning the problem that images captured by optical system suffer unsteady degradation including noise, blurring and geometric distortion when imaging process is affected by defocusing, motion, atmospheric disturbance and photoelectric noise, a generic framework of image restoration based on natural patch likelihood and sparse prior was proposed. Firstly, on the basis of natural image sparse prior model, several patch likelihood models were compared. The results indicate that the image patch likelihood model can improve the restoration performance. Secondly, the image expected patch log likelihood model was constructed and optimized, which reduced the running time and simplified the learning process. Finally, image restoration based on optimized expected log likelihood and Gaussian Mixture Model (GMM) was accomplished through the approximate Maximum A Posteriori (MAP) algorithm. The experimental results show that the proposed approach can restore degraded images by kinds of blur and additive noise, and its performance outperforms the state-of-the-art image restoration methods based on sparse prior in both Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity (SSIM) with a better visual effect.

Key words: image restoration, image patch likelihood, sparse priors, expected patch log likelihood, Gaussian Mixture Model (GMM)

中图分类号:

TP391.413

李俊山, 杨亚威, 朱子江, 张姣. 基于自然图像块相似性和稀疏先验性的图像复原[J]. 计算机应用, 2017, 37(8): 2319-2323.

LI Junshan, YANG Yawei, ZHU Zijiang, ZHANG Jiao. Image restoration based on natural patch likelihood and sparse prior[J]. Journal of Computer Applications, 2017, 37(8): 2319-2323.

参考文献

[1] CAI J F, HUI J, CHAO Q L, et al. Blind motion deblurring from a single image using sparse approximation[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2009:104-111.
[2] XU L, ZHENG S Z, JIA J. Unnatural L₀ sparse representation for natural image deblurring[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2013:1107-1114.
[3] 徐焕宇,孙权森,李大禹,等.基于投影的稀疏表示与非局部正则化图像复原方法[J].电子学报,2014,42(7):1299-1304.(XU H Y, SUN Q S, LI D Y, et al. Projection-based image restoration via space representation and nonlocal regularization[J]. Acta Electronica Sinica, 2014, 42(7):1299-1304.)
[4] REN J, LIU J Y, GUO Z M. Context-aware sparse decomposition for image denoising and super-resolution[J]. IEEE Transactions on Image Processing, 2013, 22(4):1456-1469.
[5] HUANG D, KANG L, WANG Y C F, et al. Self-learning based image decomposition with applications to single image denoising[J]. IEEE Transactions on Multimedia, 2014, 16(1):83-93.
[6] MADERO-OROZCO H, RUIZ P, MATEOS J, et al. Image deblurring combining Poisson singular integral and total variation prior models[C]//Proceedings of the 21st European Signal Processing Conference. Piscataway, NJ:IEEE, 2013:1-5.
[7] ZHANG J, ZHAO D B, XIONG R Q, et al. Image restoration using joint statistical modeling in a space-transform domain[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2014, 24(6):915-928.
[8] SHI J G, QI C. Sparse modeling based image inpainting with local similarity constraint[C]//Proceedings of the 20th IEEE International Conference on Image Processing. Piscataway, NJ:IEEE, 2013:1371-1375.
[9] YEH C, KANG L, CHIOU Y, et al. Self-learning-based post-processing for image/video deblocking via sparse representation[J]. Journal of Visual Communication Image Representation, 2014, 25(5):891-903.
[10] CHOI I, KIM S, BROWN M S, et al. A leaning-based approach to reduce JPEG artifacts in image matting[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2013:2880-2887.
[11] RAM S, RODRIGUEZ J J. Single image super-resolution using dictionary-based local regression[C]//Proceedings of the 2014 IEEE Southwest Symposium on Image Analysis and Interpretation. Piscataway, NJ:IEEE, 2014:121-124.
[12] 钟莹,杨学智,唐益明,等.采用结构自适应块匹配的非局部均值去噪算法[J].电子与信息学报,2013,35(12):2908-2916.(ZHONG Y, YANG X Z, TANG Y M, et al. Non-local means denoising derived from structure-adapted block matching[J]. Journal of Electronics & Information Technology, 2013, 35(12):2908-2916.)
[13] ZORAN D, WEISS Y. From learning models of natural image patches to whole image restoration[C]//Proceedings of the 2011 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2011:479-486.
[14] WANG R X, TRUCCO E. Single-patch low-rank prior for non-pointwise impulse noise removal[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2013:1073-1080.
[15] LEVIN A, FERGUS R, DURAND F, et al. Deconvolution using natural image priors[R]. Cambridge, MA:Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory, 2007.
[16] WEISS Y, FREEMAN W T. What makes a good model of natural images?[C]//Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2007:1-8.
[17] ROTH S, BLACK M J. Fields of experts:a framework for learning image priors[C]//Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2005:860-867.
[18] KRISHNAN D, FERGUS R. Fast image deconvolution using hyper-Laplacian priors[C]//NIPS' 09:Proceedings of the 22nd International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc., 2009:1033-1041.
[19] MARTIN D, FOWLKES C, TAL D, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]//ICCV 2001:Proceedings of the 8th International Conference on Computer Vision. Piscataway, NJ:IEEE, 2001:416-423.
[20] LINDSAY B. Composite likelihood methods[J]. Contemporary Mathematics, 1988, 80(1):221-390.
[21] DOMKE J, KARAPURKAR A, ALOIMONOS Y. Who killed the directed model?[C]//Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2008:1-8.
[22] 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.
[23] GEMAN D, YANG C. Nonlinear image recovery with half-quadratic regularization[J]. IEEE Transactions on Image Processing, 2002, 4(7):932-946.
[24] ZORAN D, WEISS Y. Scale invariance and noise in natural images[C]//Proceedings of the IEEE 12th International Conference on Computer Vision. Piscataway, NJ:IEEE, 2009:2209-2216.
[25] PORTILLA J, STRELA V, WAINWRIGHT M, et al. Image denoising using scale mixtures of Gaussians in the wavelet domain[J]. IEEE Transactions on Image Processing, 2003, 12(11):1338-1351.
[26] CARREIRA-PERPINAN M. Mode-finding for mixtures of Gaussian distributions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 22(11):1318-1323.
[27] LUCK L B. An iterative technique for the rectification of observed distributions[J]. Astronomical Journal, 1974, 79(6):745-754.
[28] RICHARDSON W. Bayesian-based iterative method of image restoration[J]. Journal of the Optical Society of America, 1972, 62(1):55-59.
[29] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.

基于自然图像块相似性和稀疏先验性的图像复原

Image restoration based on natural patch likelihood and sparse prior

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]	陈聿, 田博今, 彭云竹, 廖勇. 联合手肘法和期望最大化的高斯混合聚类电力系统客户分群算法[J]. 计算机应用, 2020, 40(11): 3217-3223.
[3]	彭磊, 杨秀云, 张裕飞, 李光耀. 基于全局与局部相似性测度的非刚性点集配准[J]. 计算机应用, 2019, 39(10): 3028-3033.
[4]	林朗, 王让定, 严迪群, 李璨. 基于修正倒谱特征的回放语音检测算法[J]. 计算机应用, 2018, 38(6): 1648-1652.
[5]	喻新荣, 李志华, 闫成雨, 李双俐. 云数据中心高效的虚拟机整合方法[J]. 计算机应用, 2018, 38(2): 550-556.
[6]	陶志勇, 刘晓芳, 王和章. 融合密度峰值的高斯混合模型聚类算法[J]. 计算机应用, 2018, 38(12): 3433-3437.
[7]	陈文兵, 管正雄, 陈允杰. 基于条件生成式对抗网络的数据增强方法[J]. 计算机应用, 2018, 38(11): 3305-3311.
[8]	陈艳, 严腾, 宋俊芳, 宋焕生. 基于高斯混合模型和AdaBoost的夜间车辆检测[J]. 计算机应用, 2018, 38(1): 260-263.
[9]	黄亮, 潘平, 周超. 基于量子隧穿效应的说话人真伪鉴别方法[J]. 计算机应用, 2017, 37(9): 2617-2620.
[10]	王之毅, 毕笃彦, 熊磊, 凡遵林, 张晓瑜. 基于稀疏编码和岭回归的文本图像复原算法[J]. 计算机应用, 2017, 37(9): 2648-2651.
[11]	刘晙, 袁培燕, 李永锋. 基于完整可见性模型的改进鲁棒OctoMap[J]. 计算机应用, 2017, 37(5): 1445-1450.
[12]	张海艳, 高尚兵. 图像分割中改进空间约束贝叶斯网络模型的应用[J]. 计算机应用, 2017, 37(3): 823-826.
[13]	皮艾迪, 喻剑, 周笑波. 基于学习的容器环境Spark性能监控与分析[J]. 计算机应用, 2017, 37(12): 3586-3591.
[14]	江贵林, 胡访宇, 石立兴. 基于呼叫详细记录数据的城市功能区识别[J]. 计算机应用, 2016, 36(7): 2046-2050.
[15]	汪海彬, 余正涛, 毛存礼, 郭剑毅. SMFCC:一种新的语音信号特征提取方法[J]. 计算机应用, 2016, 36(6): 1735-1740.