基于并列卷积神经网络的超分辨率重建

doi:10.11772/j.issn.1001-9081.2017.04.1174

计算机应用 ›› 2017, Vol. 37 ›› Issue (4): 1174-1178.DOI: 10.11772/j.issn.1001-9081.2017.04.1174

• 计算机视觉与虚拟现实 • 上一篇下一篇

基于并列卷积神经网络的超分辨率重建

欧阳宁^1,2, 曾梦萍², 林乐平^1,2

1. 认知无线电与信息处理省部共建教育部重点实验室(桂林电子科技大学), 广西桂林 541004;
2. 桂林电子科技大学信息与通信学院, 广西桂林 541004

收稿日期:2016-08-04 修回日期:2016-12-27 发布日期:2017-04-19 出版日期:2017-04-10
通讯作者: 林乐平
作者简介:欧阳宁(1972-),男,湖南宁远人,教授,主要研究方向:数字图像处理、智能信息处理;曾梦萍(1992-),女,湖北鄂州人,硕士研究生,主要研究方向:图像超分辨率重建、深度学习;林乐平(1980-),女,广西桂平人,博士,主要研究方向:模式识别、智能信息处理、图像处理。
基金资助:
国家自然科学基金资助项目（61362021，61661017）；广西自然科学基金资助项目（2013GXNSFDA019030，2014GXNSFDA118035）；认知无线电与信号处理重点实验室主任基金资助项目（CRKL160104）；广西科技创新能力与条件建设计划项目（桂科能1598025-21）；桂林科技开发项目（20150103-6）；桂林电子科技大学研究生教育创新计划项目（YJCXS201534）。

Parallel convolutional neural network for super-resolution reconstruction

OUYANG Ning^1,2, ZENG Mengping², LIN Leping^1,2

1. Key Laboratory of Cognitive Radio and Information Processing of Ministry of Education(Guilin University of Electronic Technology), Guilin Guangxi 541004, China;
2. School of Information and Communication, Guilin University of Electronic Technology, Guilin Guangxi 541004, China

Received:2016-08-04 Revised:2016-12-27 Online:2017-04-19 Published:2017-04-10
Supported by:
This work is partially supported by National Natural Science Foundation of China (61362021, 616620211017), the Natural Science Foundation of Guangxi (2013GXNSFDA019030, 2014GXNSFDA118035), the Key Laboratory Director Foundation of Cognitive Radio and Information Processing (CRKL160104), the Scientific and Technological Innovation Ability and Condition Construction Plans of Guangxi (1598025-21), the Scientific and Technological Bureau of Guilin (20150103-6), the Innovation Project of Graduate Education in Guilin University of Electronic Technology (YJCXS201534).

摘要/Abstract

摘要： 为提取更多有效特征并提高模型训练的收敛速度，提出一种基于并列卷积神经网络的超分辨率重建方法。该网络由两路不同结构的网络组成：一路为简单的残差网络，其优化残差映射比原始的映射更容易实现；另一路为增加了非线性映射的卷积神经网络，增强了网络的非线性能力。随着并行网络结构的复杂化，收敛速度慢成为突出问题。针对这个问题，在卷积层后添加正则化处理，以简化模型参数、增强特征拟合能力，最终达到加快收敛的目的。实验结果表明，与基于深度卷积神经网络算法相比，该网络结构收敛速度更快，主观视觉效果更好，峰值信噪比（PSNR）平均提高了0.2 dB。

关键词: 并列卷积神经网络, 残差网络, 非线性映射, 正则化处理, 收敛速度

Abstract: To extract more effective features and speed up the convergence of model training, a super-resolution reconstruction algorithm based on parallel convolution neural network was proposed. The network consists of two different network structures, one is a simple residual network structure, which has a easier optimal residual mapping than the original one; the other is a convolutional neural network with nonlinear mapping, which can increase the non-linearity of the network. As the complexity of the parallel network structure, the convergence speed is the key issue. Aiming at this problem, the Local Response Normalization (LRN) layer was added to the convolution layers to simplify the model parameters and enhance the feature fitting ability, thus accelerating the convergence. Experimental results show that, compared with algorithms based on deep convolutional neural network, the proposed method accelerates the convergence, improves the visual quality, and increases Peak Signal-to-Noise Ratio (PSNR) at least 0.2 dB.

Key words: parallel convolution neural network, residual network, nonlinear mapping, Local Response Normalization (LRN), convergence speed

中图分类号:

TP391.41

欧阳宁, 曾梦萍, 林乐平. 基于并列卷积神经网络的超分辨率重建[J]. 计算机应用, 2017, 37(4): 1174-1178.

OUYANG Ning, ZENG Mengping, LIN Leping. Parallel convolutional neural network for super-resolution reconstruction[J]. Journal of Computer Applications, 2017, 37(4): 1174-1178.

参考文献

[1] GLASNER D, BAGON S, IRANI M. Super-resolution from a single image[C]//Proceedings of the 2009 IEEE 12th International Conference on Computer Vision. Piscataway, NJ: IEEE, 2009: 349-356.
[2] ZHANG D, WU X. An edge-guided image interpolation algorithm via directional filtering and data fusion[J]. IEEE Transactions on Image Processing, 2006, 15(8): 2226-2238.
[3] RASTI P, DEMIREL H, ANBARJAFARI G. Image resolution enhancement by using interpolation followed by iterative back projection[C]//Proceedings of the 201321st Signal Processing and Communications Applications Conference (SIU). Piscataway, NJ: IEEE, 2013: 1-4.
[4] YANG J-C, WRIGHT J, HUANG T S, et al. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2861-2873.
[5] YANG J, WRIGHT J, HUANG T, et al. Image super-resolution as sparse representation of raw image patches[C]//Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2008: 1-8.
[6] CHANG H, YEUNG D Y, XIONG Y. Super-resolution through neighbor embedding[C]//Proceedings of the 2004 Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2004, 1: I-I.
[7] TIMOFTE R, SMET V, GOOL L. Anchored neighborhood regression for fast example-based super-resolution[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway, NJ: IEEE, 2013: 1920-1927.
[8] 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.
[9] DONG C, LOY C C, HE K, et al. Learning a deep convolutional network for image super-resolution[C]//Proceedings of the 13th European Conference on Computer Vision, LNCS 8692. Berlin: Springer, 2014: 184-199.
[10] DONG C, LOY C C, HE K, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307.
[11] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[EB/OL].[2016-03-10]. https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf.
[12] SHANKAR S, ROBERTSON D, IOANNOU Y, et al. Refining architectures of deep convolutional neural networks[EB/OL].[2016-03-01]. https://arxiv.org/pdf/1604.06832v1.pdf.
[13] NAIR V, HINTON G E. Rectified linear units improve restricted Boltzmann machines[EB/OL].[2016-03-01]. http://machinelearning.wustl.edu/mlpapers/paper_files/icml2010_NairH10.pdf.
[14] BENGIO Y, SIMARD P, FRASCONI P. Learning long-term dependencies with gradient descent is difficult[J]. IEEE Transactions on Neural Networks, 1994, 5(2): 157-166.
[15] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[EB/OL].[2016-03-01]. https://arxiv.org/pdf/1512.03385v1.pdf.
[16] SZEGEDY C, IOFFE S, VANHOUCKE V. Inception-v4, inception-ResNet and the impact of residual connections on learning[EB/OL].[2016-03-01]. https://arxiv.org/pdf/1602.07261.pdf.
[17] BISHOP C M. Neural Networks for Pattern Recognition[M]. Oxford: Oxford University Press, 1995.
[18] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

基于并列卷积神经网络的超分辨率重建

Parallel convolutional neural network for super-resolution reconstruction

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]	刘源泂, 何茂征, 黄益斌, 钱程. 基于ResNet50和改进注意力机制的船舶识别模型[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1935-1941.
[2]	郭琳, 刘坤虎, 马晨阳, 来佑雪, 徐映芬. 基于感受野扩展残差注意力网络的图像超分辨率重建[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1579-1587.
[3]	付顺旺, 陈茜, 李智, 王国美, 卢妤. 用于篡改图像检测和定位的双通道渐进式特征过滤网络[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1303-1309.
[4]	周景贤, 李希娜. 基于改进卷积神经网络和射频指纹的无人机检测与识别[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 876-882.
[5]	黄学雨, 贺怀宇, 林慧敏, 陈金水. 基于特征聚合的铜合金金相图分类识别方法[J]. 《计算机应用》唯一官方网站, 2023, 43(8): 2593-2601.
[6]	张慧斌, 冯丽萍, 郝耀军, 王一宁. 基于注意力机制和迁移学习的古壁画朝代识别[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1826-1832.
[7]	申利华, 李波. 基于特征金字塔网络和密集网络的肺部CT图像超分辨率重建[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1612-1619.
[8]	宋其洪, 刘建勋, 扈海泽, 张祥平. 基于协同融合网络的代码搜索模型[J]. 《计算机应用》唯一官方网站, 2023, 43(12): 3896-3902.
[9]	张志昂, 廖光忠. 基于U-Net的多尺度特征增强视网膜血管分割算法[J]. 《计算机应用》唯一官方网站, 2023, 43(10): 3275-3281.
[10]	廖列法, 李志明, 张赛赛. 基于深度残差网络的迭代量化哈希图像检索方法[J]. 《计算机应用》唯一官方网站, 2022, 42(9): 2845-2852.
[11]	贺怀清, 闫建青, 惠康华. 基于深度残差网络的轻量级人脸识别方法[J]. 《计算机应用》唯一官方网站, 2022, 42(7): 2030-2036.
[12]	沙林秀, 聂凡, 高倩, 孟号. 基于布朗运动与梯度信息的交替优化算法[J]. 《计算机应用》唯一官方网站, 2022, 42(7): 2139-2145.
[13]	张杨, 郝江波. 基于注意力机制和残差网络的恶意代码检测方法[J]. 《计算机应用》唯一官方网站, 2022, 42(6): 1708-1715.
[14]	董明宇, 严迪群. 基于ResNet的音频场景声替换造假的检测算法[J]. 《计算机应用》唯一官方网站, 2022, 42(6): 1724-1728.
[15]	王汇丰, 徐岩, 魏一铭, 王会真. 基于并联卷积与残差网络的图像超分辨率重建[J]. 《计算机应用》唯一官方网站, 2022, 42(5): 1570-1576.