2.793

2018影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于深度特征学习的图像超分辨率重建

胡长胜 詹曙 吴从中

胡长胜, 詹曙, 吴从中. 基于深度特征学习的图像超分辨率重建. 自动化学报, 2017, 43(5): 814-821. doi: 10.16383/j.aas.2017.c150634
引用本文: 胡长胜, 詹曙, 吴从中. 基于深度特征学习的图像超分辨率重建. 自动化学报, 2017, 43(5): 814-821. doi: 10.16383/j.aas.2017.c150634
HU Chang-Sheng, ZHAN Shu, WU Cong-Zhong. Image Super-resolution Based on Deep Learning Features. ACTA AUTOMATICA SINICA, 2017, 43(5): 814-821. doi: 10.16383/j.aas.2017.c150634
Citation: HU Chang-Sheng, ZHAN Shu, WU Cong-Zhong. Image Super-resolution Based on Deep Learning Features. ACTA AUTOMATICA SINICA, 2017, 43(5): 814-821. doi: 10.16383/j.aas.2017.c150634

基于深度特征学习的图像超分辨率重建

doi: 10.16383/j.aas.2017.c150634
基金项目: 

中科院自动化所复杂系统管理与控制国家重点实验室开放课题 20130107

安徽省科技攻关项目基金 1401B042019

国家自然科学基金 61371156

详细信息
    作者简介:

    胡长胜  合肥工业大学硕士研究生.2014年获得安徽师范大学物理与电子信息学院通信工程系学士学位.主要研究方向为图像超分辨率重建.E-mail:hucley@mail.hfut.edu.cn

    吴从中  合肥工业大学计算机与信息学院副教授.主要研究方向为信号处理.E-mail:zhanshuhfut@163.com

    通讯作者:

    詹曙  合肥工业大学计算机与信息学院教授.分别于1990年和1993年获得合肥工业大学电子工程系学士学位和硕士学位.2000年获得中国科学技术大学博士学位.2002~2005年日本东京大学, 进行博士后研究.主要研究方向为模式识别, 计算机视觉和医学图像处理..E-mail:shuzhan@hfut.edu.cn

Image Super-resolution Based on Deep Learning Features

Funds: 

State Key Laboratory of Management and Control for Complex System of Institute of Automation Chinese Academy of Sciences Open Project 20130107

Anhui Province Science and Technology Research Programs 1401B042019

National Natural Science Foundation of China 61371156

More Information
    Author Bio:

     Master student at the Hefei University of Technology. He received his bachelor degree from Anhui Normal University in 2014. His main research interest is image super-resolution

     Associate professor at the School of Computer and information, Hefei University of Technology. His main research interest is signal processing

    Corresponding author: ZHAN Shu  Professor at the School of Computer and Information, Hefei University of Technology, China. He received his bachelor and master degrees in electronic engineering from the Hefei University of Technology in 1990 and 1993, China and the Ph.\, D. degree in electronic engineering from University of Science and Technology of China in 2000. He was a postdoctor at the University of Tokyo from 2002\, $\sim$\, 2005, Japan. His research interest covers pattern recognition, computer vision and medical imaging. Corresponding author of this paper
  • 摘要: 基于学习的图像超分辨率(Super-resolution,SR)算法利用样本先验知识来重建图像,相较于其他重建方法拥有明显的优势,也是近年来研究的热点.论文首先分析了影响图像重建质量的因素,然后对基于卷积神经网络的图像超分辨率重建算法(Super-resolution convolutional neural network,SRCNN)提出了两点改进:我们用随机线性纠正单元(Randomized rectified linear unit,RReLU)去避免原有网络学习中对图像某些重要的信息过压缩,同时我们用NAG(Nesterov's accelerated gradient)方法去加速网络的收敛并且避免了网络在梯度更新的时候产生较大的震荡.最后通过实验验证了我们改进网络可以获得更好的主观视觉评价和客观量化评价.
  • 图  1  ReLU函数的示意图

    Fig.  1  An illustration of ReLU

    图  2  RReLU函数的示意图

    (其中 $a_{ji}$ 为在抽样给定范围类的一个随机变量, 同时为了方便, 在测试阶段, 我们通常根据实际情况取一个固定值来进行测试)

    Fig.  2  An illustration of RReLU

    ( $a_{ji}$ is a random variable of in the given sampling scope. And in the testing phase, we usually take a fixed value to test according to actual condition.)

    图  3  超分重建卷积神经网络结构示意图

    Fig.  3  The structure chart of CNN for super-resolution

    图  4  NAG方法更新方法示意

    (首先按照原有路径方向更新一个步长(黑色虚线向量), 计算该位置的梯度值(灰色虚线向量), 然后用这个梯度值进行修正, 得到最终的更新方向(黑色实线向量).图中描述了NAG更新两步的示意图, 其中灰色实线向量表示CM方法更新路径)

    Fig.  4  An illustration of NAG method

    (which updates a step (the black dotted line vector in the figure) according to the original path direction, firstly. Then calculating the gradient value of the current position and correcting the update path (the gray dotted line vector in the figure). The black line vector is the final path of NAG and the gray line vector is the update path of CM.)

    图  5  在Set 5测试集上, 随着迭代系数的增加, 不同方法的Test Loss曲线图

    Fig.  5  The curve of Test Loss in Set 5 for different methods with the number of iterations increasing

    图  6  在Set 5测试集上, 随着迭代系数的增加, 不同方法的平均PSNR (dB)值的走势

    Fig.  6  The average value of PSNR (dB) for different methods with the number of iterations increasing

    图  7  Set 5中的Baby_GT重建对比图

    Fig.  7  The quality of reconstruction comparison for image Baby_GT in Set 5

    图  8  Set 5中的Bird_GT重建对比图

    Fig.  8  The quality of reconstruction comparison for image Bird_GT in Set 5

    图  9  Set 14中的Face重建对比图

    Fig.  9  The quality of reconstruction comparison for image Face in Set 14

    图  10  Set 14中的Pepper重建对比图

    Fig.  10  The quality of reconstruction comparison for image Pepper in Set 14

    图  11  网络对Baby学习到的信息

    Fig.  11  The information learned by network for Baby

    表  1  在Set 5测试集上的PSNR (dB), SSIM

    Table  1  PSNR (dB) and SSIM for Set 5

    图片 双三次插值 ScSR[10] SRCNN[14] 本文方法
    Baby 33.91 34.29 34.42 34.85
    Bird 32.58 34.11 33.35 35.02
    Butterfly 24.04 25.58 27.89 27.73
    Head 32.87 33.17 31.79 33.44
    Woman 28.56 29.94 30.67 30.8
    Average 30.96 31.42 31.62 32.37
    SSIM 0.8687 0.8821 0.889 0.9039
    下载: 导出CSV

    表  2  在Set 14测试集上的平均PSNR (dB), SSIM

    Table  2  The average PSNR (dB) and SSIM for Set 14

    图片 双三次插值 ScSR[9] SRCNN[11] 本文方法
    PSNR 27.47 28.19 28.84 28.92
    SSIM 0.7722 0.7977 0.8137 0.8178
    下载: 导出CSV
  • [1] Tsai R Y, Huang T S. Multiple frame image restoration and registration. Advances in Computer Vision and Image Processing. Greenwich: JAI, 1984. 317-339
    [2] Baker S, Kanade T. Limits on super-resolution and how to break them. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(9): 1167-1183
    [3] 苏衡, 周杰, 张志浩.超分辨率图像重建方法综述.自动化学报, 2013, 39(8): 1202-1213 http://www.aas.net.cn/CN/abstract/abstract18151.shtml

    Su Heng, Zhou Jie, Zhang Zhi-Hao. Survey of super-resolution image reconstruction methods. Acta Automatica Sinica, 2013, 39(8): 1202-1213 http://www.aas.net.cn/CN/abstract/abstract18151.shtml
    [4] Zhou F, Yang W M, Liao Q M. Interpolation-based image super-resolution using multisurface fitting. IEEE Transactions on Image Processing, 2012, 21(7): 3312-3318 doi: 10.1109/TIP.2012.2189576
    [5] Lin Z C, Shum H Y. Fundamental limits of reconstruction-based superresolution algorithms under local translation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1): 83-97 doi: 10.1109/TPAMI.2004.1261081
    [6] 潘宗序, 禹晶, 胡少兴, 孙卫东.基于多尺度结构自相似性的单幅图像超分辨率算法.自动化学报, 2014, 40(4): 594-603 http://www.aas.net.cn/CN/abstract/abstract18325.shtml

    Pan Zong-Xu, Yu Jing, Hu Shao-Xing, Sun Wei-Dong. Single image super resolution based on multi-scale structural self-similarity. Acta Automatica Sinica, 2014, 40(4): 594-603 http://www.aas.net.cn/CN/abstract/abstract18325.shtml
    [7] 练秋生, 石保顺, 陈书贞.字典学习模型、算法及其应用研究进展.自动化学报, 2015, 41(2): 240-260 http://www.aas.net.cn/CN/abstract/abstract18604.shtml

    Lian Qiu-Sheng, Shi Bao-Shun, Chen Shu-Zhen. Research advances on dictionary learning models, algorithms and applications. Acta Automatica Sinica, 2015, 41(2): 240-260 http://www.aas.net.cn/CN/abstract/abstract18604.shtml
    [8] Freeman W T, Jones T R, Pasztor E C. Example-based super-resolution. IEEE Computer Graphics and Applications, 2002, 22(2): 56-65 doi: 10.1109/38.988747
    [9] Polatkan G, Zhou M Y, Carin L, Blei D, Daubechies I. A Bayesian nonparametric approach to image super-resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(2): 346-358 doi: 10.1109/TPAMI.2014.2321404
    [10] Yang J C, Wright J, Huang T S, Ma Y. Image super-resolution via sparse representation. IEEE Transactions on Image Processing, 2010, 19(11): 2861-2873 doi: 10.1109/TIP.2010.2050625
    [11] Yu D, Deng L. Deep learning and its applications to signal and information processing. IEEE Signal Processing Magazine, 2011, 28(1): 145-154 doi: 10.1109/MSP.2010.939038
    [12] Yu D, Deng L, Seide F. The deep tensor neural network with applications to large vocabulary speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, 2013, 21(2): 388-396 doi: 10.1109/TASL.2012.2227738
    [13] Hutchinson B, Deng L, Yu D. Tensor deep stacking networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 1944-1957 doi: 10.1109/TPAMI.2012.268
    [14] Dong C, Loy C C, He K M, Tang X O. Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307 doi: 10.1109/TPAMI.2015.2439281
    [15] Cui Z, Chang H, Shan S G, Zhong B E, Chen X L. Deep network cascade for image super-resolution. In: Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland: Springer, 2014. 49-64
    [16] Xu B, Wang N Y, Chen T Q, Li M. Empirical evaluation of rectified activations in convolutional network. In: Proceedings of the 32th International Conference on Machine Learning: Deep Learning Workshop. Lille, France: ICML, 2015.
    [17] Nesterov Y. A method of solving a convex programming problem with convergence rate O(1/k2). Soviet Mathematics Doklady, 1983, 27(2): 372-376
    [18] Sutskever I, Martens J, Dahl G, Hinton G. On the importance of initialization and momentum in deep learning. In: Proceedings of the 30th International Conference on Machine Learning. Atlanta, Georgia, USA: JMLR, 2013. 1139-1147
    [19] Jia Y Q, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T. Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia. Orlando, Florida, USA: ACM, 2014. 675-678
    [20] Nair V, Hinton G F. Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning. Haifa, Israel: ICML, 2010. 807-814
    [21] Nesterov Y. Introductory Lectures on Convex Optimization: A Basic Course. US: Springer, 2004. 63-66
    [22] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. In: Proceedings of the 26th Annual Conference on Neural Information Processing Systems. Lake Tahoe, USA: Curran Associates, Inc., 2012. 25(2): 1097-1105
    [23] He K M, Zhang X Y, Ren S Q, Sun J. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the 2015 IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2015. 1026-1034
    [24] Lan G H. An optimal method for stochastic composite optimization. Mathematical Programming, 2012, 133(1-2): 365-397 doi: 10.1007/s10107-010-0434-y
    [25] Bevilacqua M, Roumy A, Guillemot C, Morel M L A. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: Proceedings of the 2012 British Machine Vision Conference. Guildford, UK: University of Surrey, 2012.
    [26] Zeyde R, Elad M, Protter M. On single image scale-up using sparse-representations. In: Proceedings of the 7th International Conference on Curves and Surfaces. Avignon, France: Springer, 2010. 711-730
  • 加载中
图(11) / 表(2)
计量
  • 文章访问数:  1912
  • HTML全文浏览量:  737
  • PDF下载量:  1817
  • 被引次数: 0
出版历程
  • 收稿日期:  2015-10-13
  • 录用日期:  2016-06-17
  • 刊出日期:  2017-05-01

目录

    /

    返回文章
    返回