基于图像块分类的图像超分辨率重建

doi:10.11772/j.issn.1001-9081.2018061368

计算机应用 ›› 2019, Vol. 39 ›› Issue (2): 577-581.DOI: 10.11772/j.issn.1001-9081.2018061368

• 虚拟现实与多媒体计算 • 上一篇下一篇

基于图像块分类的图像超分辨率重建

杜凯敏, 康宝生

西北大学信息科学与技术学院, 西安 710127

收稿日期:2018-07-02 修回日期:2018-09-03 发布日期:2019-02-15 出版日期:2019-02-10
通讯作者: 康宝生
作者简介:杜凯敏(1993-),女,山西壶关人,硕士研究生,主要研究方向:图像超分辨率重建;康宝生(1961-),男,陕西咸阳人,教授,博士生导师,博士,主要研究方向:图形图像处理。

Image super-resolution reconstruction based on image patch classification

DU Kaimin, KANG Baosheng

School of Information Science & Technology, Northwest University, Xi'an Shaanxi 710127, China

Received:2018-07-02 Revised:2018-09-03 Online:2019-02-15 Published:2019-02-10

摘要/Abstract

摘要： 针对当前图像超分辨率重建算法中存在的字典单一而导致重建图像质量不佳的问题，提出一种将图像块分类与图像卡通纹理分解相结合的单幅图像超分辨率重建算法。首先，将图像分块，并将图像块分为边缘类、纹理类和平滑类三类，其中纹理类用形态成分分析（MCA）算法分解为卡通部分和纹理部分；然后，对边缘类、卡通部分和纹理部分分别训练高低分辨率字典；最后，求解稀疏系数并与高分辨率字典重建图像块。仿真结果显示，与基于稀疏表示的超分辨率重建（SCSR）算法和单幅图像超分辨率重建（SISR）算法相比，所提算法的峰值信噪比（PNSR）值分别提高了0.26 dB和0.14 dB，表明该算法的重建效果更好，重建图像纹理细节更丰富。

关键词: 图像重建, 图像块分类, 卡通纹理, 稀疏表示, K奇异值分解

Abstract: Concerning the poor quality of existing image super-resolution reconstruction caused by single dictionary, a new single image super-resolution algorithm based on classified image patches and image cartoon-texture decomposition was proposed. Firstly, an image was divided into image patches which were classified into smooth patches, edge patches and texture patches, and the texture class was divided into cartoon part and texture part by Morphological Component Analysis (MCA) algorithm. Secondly, ege patches, cartoon part and texture part of texture patches were applied respectively to train the dictionaries of low-resolution and high-resolution. Finally, the sparse coefficients were calculated, then the image patches were reconstructed by using the corresponding high-resolution dictionary and sparse coefficients. In the comparison experiments with Sparse Coding Super-Resolution (SCSR) algorithm and Single Image Super-Resolution (SISR) algorithm, the Peak Signal-to-Noise Ratio (PSNR) of the proposed algorithm was increased by 0.26 dB and 0.14 dB respectively. The experimental results show that the proposed algorithm can obtain more details in texture with better reconstruction effect.

Key words: image reconstruction, image patch classification, cartoon-texture, sparse representation, K-Singular Value Decomposition (K-SVD)

中图分类号:

TP391.41

杜凯敏, 康宝生. 基于图像块分类的图像超分辨率重建[J]. 计算机应用, 2019, 39(2): 577-581.

DU Kaimin, KANG Baosheng. Image super-resolution reconstruction based on image patch classification[J]. Journal of Computer Applications, 2019, 39(2): 577-581.

参考文献

[1] ZHOU D. An edge-directed bicubic interpolation algorithm[C]//Proceedings of the 20103rd International Congress on Image and Signal Proncessing. Piscataway, NJ:IEEE, 2010:1186-1189.
[2] 陶志强,李海林,张红兵.基于新边缘指导插值的迭代反投影超分辨率重建算法[J].计算机工程,2016,42(6):255-260. (TAO Z Q, LI H L, ZHANG H B. Iterative back projection super resolution reconstruction algorithm based on new edge directed interpolation[J]. Computer Engineering, 2016, 42(6):255-260.)
[3] 曾凯,丁世飞.图像超分辨率重建的研究进展[J].计算机工程与应用,2017,53(16):29-35. (ZENG K, DING S F. Advances in image super-resolution reconstruction[J]. Computer Engineering and Applications,2017,53(16):29-35.)
[4] DONG C, CHEN C L, HE K, et al. Learning a deep convolutional network for image super-resolution[C]//Proceedings of the 2014 European Conference on Computer Vision, LNCS 8692. Cham:Springer, 2014:184-199.
[5] KIM J, LEE J K, LEE K M. Deeply-recursive convolutional network for image super-resolution[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:1637-1645.
[6] LEDIG C, THEIS L, HUSZAR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//Proceedings of the 2017 Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2017:105-114.
[7] YANG J, WRIGHT J, HUANG T, et al. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11):2861-2873.
[8] YANG J, WANG Z W, LIN Z, et al. Coupled dictionary learning for image super-resolution[J]. IEEE Transactions on Image Processing, 2012, 21:3467-3478.
[9] CANDES E J, WAKIN M B. An introduction to compressive sampling[J]. IEEE Signal Processing Magazine, 2008, 25(2):21-30.
[10] 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.
[11] AHARON M, ELAD M, BRUCKSTEIN A, et al. K-SVD:an algorithm for designing of overcomplete dictionaries for sparse representation[J]. IEEE Transactions on Signal Processing, 2006, 54(11):4311-4322.
[12] RUBINSTEIN R, ZIBULEVSKY M, ELAD M. Efficient implementation of the K-SVD algorithm using batch orthogonal matching pursuit[R]. Technion, Israel:Technion University, 2008:1-15.
[13] 张晓燕,秦龙龙,钱渊,等.一种改进的稀疏表示超分辨率重建算法[J].重庆邮电大学学报(自然科学版),2016,28(3):400-405. (ZHANG X Y, QIN L L, QIAN Y, et al. An improved sparse representation of super resolution reconstruction algorithm[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2016, 28(3):400-405.)
[14] 王旸.超分辨率图像重建效果优化算法研究[J].控制工程,2018,25(5):740-745.(WANG Y. An optimal algorithm for super-resolution image reconstruction[J]. Control Engineering of China, 2018, 25(5):740-745.)
[15] 徐川. 基于卡通纹理分解和稀疏表示的图像超分辨率重建[J]. 软件工程,2016,19(5):2096-1472. (XU C. Image super-resolution reconstruction based on cartoon-texture decomposition and sparse representation[J]. Software Engineering, 2016, 19(5):2096-1472.)
[16] 练秋生, 张伟. 基于图像块分类稀疏表示的超分辨率重构算法[J]. 电子学报,2012,40(5):920-925.(LIAN Q S,ZHANG W. Image Super-resolution algorithms based on sparse representation of classified image patches[J]. Acta Electronica Sinica, 2012, 40(5):920-925.)

基于图像块分类的图像超分辨率重建

Image super-resolution reconstruction based on image patch classification

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]	邱华禄, 蔺素珍, 王彦博, 刘峰, 李大威. 基于复卷积双域级联网络的欠采样磁共振图像重建算法[J]. 《计算机应用》唯一官方网站, 2024, 44(2): 580-587.
[2]	樊小宇, 蔺素珍, 王彦博, 刘峰, 李大威. 基于残差图卷积神经网络的高倍欠采样核磁共振图像重建算法[J]. 《计算机应用》唯一官方网站, 2023, 43(4): 1261-1268.
[3]	包永春, 张建臣, 杜守信, 张军军. 基于非负矩阵分解与稀疏表示的多标签分类算法[J]. 《计算机应用》唯一官方网站, 2022, 42(5): 1375-1382.
[4]	李昆鹏, 张鹏程, 上官宏, 王燕玲, 杨婕, 桂志国. 基于卷积神经网络的时频域CT重建算法[J]. 《计算机应用》唯一官方网站, 2022, 42(4): 1308-1316.
[5]	林乐平, 周宏敏, 欧阳宁. 融合空间位置与结构信息的压缩感知图像重建方法[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 930-937.
[6]	裴春阳, 樊宽刚, 马政. 基于边缘保留分解和改进稀疏表示的医学图像融合[J]. 计算机应用, 2021, 41(7): 2092-2099.
[7]	任晓奎, 刘鹏飞, 陶志勇, 刘影, 白立春. 基于单快拍信号到达角估计算法的室内入侵检测[J]. 计算机应用, 2021, 41(4): 1153-1159.
[8]	王丽娟, 陈少敏, 尹明, 许跃颖, 郝志峰, 蔡瑞初, 温雯. 基于近邻图改进的块对角子空间聚类算法[J]. 计算机应用, 2021, 41(1): 36-42.
[9]	席雅睿, 乔志伟, 温静, 张艳娇, 杨雯晶, 闫慧文. 基于Chambolle-Pock算法框架的高阶TV图像重建算法[J]. 计算机应用, 2020, 40(6): 1793-1798.
[10]	王治忠, 庞晨. 基于鸽视顶盖神经元动作电位的图像重建[J]. 计算机应用, 2020, 40(3): 832-836.
[11]	高彦彦, 李莉, 张晶, 贾英茜. 结合梯度投影稀疏重构和复数小波的图像重构[J]. 《计算机应用》唯一官方网站, 2020, 40(2): 486-490.
[12]	叶杨, 蔡琼, 杜晓标. 基于非局部通道注意力机制的单图像超分辨率方法[J]. 计算机应用, 2020, 40(12): 3618-3623.
[13]	宗春梅, 张月琴, 曹建芳, 赵青杉. 基于深度先验及非局部相似性的压缩感知核磁共振成像[J]. 计算机应用, 2020, 40(10): 3054-3059.
[14]	杜年茂, 徐佳陈, 肖志勇. 基于卷积神经网络的欠采样脑部核磁共振图像重建方法[J]. 计算机应用, 2020, 40(10): 3060-3065.
[15]	王文杰, 乔志伟, 牛蕾, 席雅睿. 自适应步长非局部全变分约束迭代图像重建算法[J]. 计算机应用, 2020, 40(1): 245-251.