基于级联深度卷积神经网络的高性能图像超分辨率重构

doi:10.11772/j.issn.1001-9081.2017.11.3124

计算机应用 ›› 2017, Vol. 37 ›› Issue (11): 3124-3127.DOI: 10.11772/j.issn.1001-9081.2017.11.3124

• 第十六届中国机器学习会议(CCML 2017) • 上一篇下一篇

基于级联深度卷积神经网络的高性能图像超分辨率重构

郭晓¹, 谭文安^1,2

1. 南京航空航天大学计算机科学与技术学院, 南京 211106;
2. 上海第二工业大学计算机与信息学院, 上海 201209

收稿日期:2017-05-16 修回日期:2017-06-05 出版日期:2017-11-10 发布日期:2017-11-11
通讯作者: 谭文安
作者简介:郭晓(1994-),男,江苏南京人,硕士研究生,主要研究方向:机器学习、深度学习、图像重建;谭文安(1965-),男,湖北荆州人,教授,博士,主要研究方向:软件服务工程、可信服务计算与组合、协同计算、业务过程智能。
基金资助:
国家自然科学基金资助项目（61672022）。

High-performance image super-resolution restruction based on cascade deep convolutional network

GUO Xiao¹, TAN Wenan^1,2

1. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing Jiangsu 211106, China;
2. College of Computer and Information, Shanghai Polytechnic University, Shanghai 201209, China

Received:2017-05-16 Revised:2017-06-05 Online:2017-11-10 Published:2017-11-11
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61672022).

摘要/Abstract

摘要： 为了进一步提高现有图像超分辨率重构方法所得图像的分辨率，提出一种高性能的深度卷积神经网络（HDCN）模型用于重构放大倍数固定的超分辨率图像。通过建立级联HDCN模型解决传统模型重构图像时放大倍数无法按需选择的问题，并在级联过程中引入深度边缘滤波器以减少级联误差，突出边缘信息，从而得到高性能的级联深度卷积神经网络（HCDCN）模型。基于Set5、Set14数据集进行超分辨率图像重构实验，证明了引入深度边缘滤波器的有效性，对比HCDCN方法与其他图像超分辨率重构方法的性能评估结果，展现了HCDCN方法的优越性能。

关键词: 超分辨率, 图像重建, 深度卷积神经网络, 级联, 深度边缘滤波器

Abstract: In order to further improve the resolution of existing image super-resolution methods, a High-performance Deep Convolution neural Network (HDCN) was proposed to reconstruct a fixed-scale super-resolution image. By cascading several HDCN models, the problem that many traditional models could not upscale images in alternative scale factors was solved, and a deep edge filter in the cascade process was introduced to reduce cascading errors, and highlight edge information, High-performance Cascade Deep Convolutional neural Network (HCDCN) was got. The super-resolution image reconstruction experiment was carried out on high-performance cascade deep convolution neural network (HCDCN) model on Set5 and Set14 datasets. The experimental results prove the effectiveness of introducing the deep edge-aware filter. By comparing the performance evaluation results of HCDCN method and other image super-resolution reconstruction method, the superior performance of HCDCN method is demonstrated.

Key words: super-resolution, image reconstruction, deep convolutional neural network, cascade, deep edge-aware filter

中图分类号:

TP391.41

郭晓, 谭文安. 基于级联深度卷积神经网络的高性能图像超分辨率重构[J]. 计算机应用, 2017, 37(11): 3124-3127.

GUO Xiao, TAN Wenan. High-performance image super-resolution restruction based on cascade deep convolutional network[J]. Journal of Computer Applications, 2017, 37(11): 3124-3127.

参考文献

[1] KEYS R. Cubic convolution interpolation for digital image processing[J]. IEEE Transactions on Acoustics, Speech and Signal Processing, 1981, 29(6):1153-1160.
[2] 曾坤. 基于学习的单幅图像超分辨率重建的若干关键问题研究[D]. 厦门:厦门大学, 2015.(ZENG K. Research on some key problems of single image super-resolution reconstruction based on learning[D]. Xiamen:Xiamen University, 2015.)
[3] IRANI M, PELEG S. Improving resolution by image registration[J]. Graphical Models and Image Processing, 1991, 53(3):231-239.
[4] 曾俊国. 基于稀疏邻域嵌入法的图像超分辨技术研究[J]. 科学技术与工程, 2013, 13(7):1840-1846.(ZENG J G. Image super resolution based on sparse neighbor embedding[J]. Science Technology and Engineering, 2013, 13(7):1840-1846.)
[5] 沈松, 朱飞, 姚琦,等. 基于稀疏表示的超分辨率图像重建[J]. 电子测量技术, 2011, 34(6):37-39.(SHEN S, ZHU F, YAO Q, et al. Based on sparse representation for super-resolution image reconstruction[J]. Electronic Measurement Technology, 2011, 34(6):37-39.)
[6] DONG C, CHEN C L, HE K, et al. Learning a Deep Convolutional Network for Image Super-Resolution[M]. Berlin:Springer International Publishing, 2014:184-199.
[7] DONG C, CHEN C L, TANG X. Accelerating the super-resolution convolutional neural network[C]//Proceedings of the 14th European Conference on Computer Vision. Berlin:Springer, 2016:391-407.
[8] KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:1646-1654.
[9] SHI W, CABALLERO J, HUSZÁR F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:1874-1883.
[10] FREEMAN W T, ADELSON E H. The design and use of steerable filters[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1991, 13(9):891-906.
[11] TOMASI C, MANDUCHI R. Bilateral filtering for gray and color images[C]//Proceedings of the Sixth International Conference on Computer Vision. Piscataway, NJ:IEEE, 1998:839.
[12] YANG Q, TAN K H, AHUJA N. Real-time O(1) bilateral filtering[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2009:557-564.
[13] YANG Q, WANG S, AHUJA N. SVM for edge-preserving filtering[C]//Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2010:1775-1782.
[14] XU L, REN J S, YAN Q, et al. Deep edge-aware filters[EB/OL].[2016-10-20]. http://www.jimmyren.com/papers/Poster_ICML-2015.pdf.
[15] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2016:770-778.
[16] CUI Z, CHANG H, SHAN S, et al. Deep network cascade for image super-resolution[C]//Proceedings of the 13th European Conference on Computer Vision. Berlin:Springer, 2014:49-64.
[17] WANG Z, LIU D, YANG J, et al. Deep networks for image super-resolution with sparse prior[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2015:370-378.
[18] 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.
[19] BEVILACQUA M, ROUMY A, GUILLEMOT C, et al. Low-complexity single-image super-resolution based on nonnegative neighbor embedding[EB/OL].[2016-10-20].http://www.irisa.fr/prive/Aline.Roumy/publi/12bmvc_Bevilacqua_lowComplexitySR.pdf.
[20] 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. Berlin:Springer-Verlag, 2010:711-730.
[21] JIA Y, SHELHAMER E, DONAHUE J, et al. Caffe:convolutional architecture for fast feature embedding[C]//Proceedings of the 22nd ACM International Conference on Multimedia. New York:ACM, 2014:675-678.
[22] TIMOFTE R, SMET V D, GOOL L V. A⁺:adjusted anchored neighborhood regression for fast super-resolution[C]//Proceedings of the 12th Asian Conference on Computer Vision. Berlin:Springer, 2015:111-126.
[23] SCHULTER S, LEISTNER C, BISCHOF H. Fast and accurate image upscaling with super-resolution forests[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2015:3791-3799.
[24] HUANG J B, SINGH A, AHUJA N. Single image super-resolution from transformed self-exemplars[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2015:5197-5206.
[25] CHEN Y, POCK T. Trainable nonlinear reaction diffusion:a flexible framework for fast and effective image restoration[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 39(6):1256-1272.

基于级联深度卷积神经网络的高性能图像超分辨率重构

High-performance image super-resolution restruction based on cascade deep convolutional network

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]	徐丽云, 闫涛, 钱宇华. 基于级联混沌系统的分数域语音加密算法[J]. 计算机应用, 2021, 41(9): 2623-2630.
[2]	卞凌志, 王直杰. 基于增强多维多粒度级联森林的信用评分模型[J]. 计算机应用, 2021, 41(9): 2539-2544.
[3]	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.
[4]	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.
[5]	卞鹏程, 郑忠龙, 李明禄, 何依然, 王天翔, 张大伟, 陈丽媛. 基于注意力融合网络的视频超分辨率重建[J]. 计算机应用, 2021, 41(4): 1012-1019.
[6]	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.
[7]	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.
[8]	李萌, 秦品乐, 曾建潮, 李俊伯. 基于磁共振影像层间插值的超分辨率及多视角融合[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3362-3367.
[9]	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.
[10]	胡高鹏, 陈子鎏, 王晓明, 张开放. 基于深度渐进式反投影注意力网络的图像超分辨率重建[J]. 计算机应用, 2020, 40(7): 2077-2083.
[11]	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.
[12]	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.
[13]	代强, 程曦, 王永梅, 牛子未, 刘飞. 基于轻量自动残差缩放网络的图像超分辨率重建[J]. 计算机应用, 2020, 40(5): 1446-1452.
[14]	喻光继, 罗伟泰, 吴肖云. 基于改进体素锥追踪的大规模场景光照计算[J]. 计算机应用, 2020, 40(5): 1421-1424.
[15]	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.