结合降噪卷积神经网络和条件生成对抗网络的图像双重盲降噪算法

doi:10.11772/j.issn.1001-9081.2020091355

计算机应用 ›› 2021, Vol. 41 ›› Issue (6): 1767-1774.DOI: 10.11772/j.issn.1001-9081.2020091355

所属专题：多媒体计算与计算机仿真

• 多媒体计算与计算机仿真 • 上一篇下一篇

结合降噪卷积神经网络和条件生成对抗网络的图像双重盲降噪算法

井贝贝¹, 郭嘉², 王丽清¹, 陈静¹, 丁洪伟¹

1. 云南大学信息学院, 昆明 650500;
2. 云南省广播电视局科技处, 昆明 650000

收稿日期:2020-09-03 修回日期:2020-11-01 出版日期:2021-06-10 发布日期:2020-12-01
通讯作者: 丁洪伟
作者简介:井贝贝(1993-),男,河南洛阳人,硕士研究生,主要研究方向:图像处理、神经网络;郭嘉(1981-),男,云南昆明人,副教授,博士,主要研究方向:无线电通信;王丽清(1971-),女,云南昆明人,副研究员,博士,主要研究方向:智能信息处理、移动网络;陈静(1982-),女,云南昆明人,讲师,硕士,主要研究方向:机器学习、图像处理;丁洪伟(1964-),男,云南昆明人,教授,博士,主要研究方向:机器学习、图像处理。
基金资助:
国家自然科学基金资助项目（61461053）；云南大学服务云南行动计划项目（C176240501007）。

Image double blind denoising algorithm combining with denoising convolutional neural network and conditional generative adversarial net

JING Beibei¹, GUO Jia², WANG Liqing¹, CHEN Jing¹, DING Hongwei¹

1. School of Information Science and Engineering, Yunnan University, Kunming Yunnan 650500, China;
2. Technology Department, Yunnan Radio and Television Bureau, Kunming Yunnan 650000, China

Received:2020-09-03 Revised:2020-11-01 Online:2021-06-10 Published:2020-12-01
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61461053), the Yunnan University Servicing Yunnan Action Program (C176240501007).

摘要/Abstract

摘要： 针对图像降噪中降噪效果差、计算效率低的问题，提出了一种结合降噪卷积神经网络（DnCNN）和条件生成对抗网络（CGAN）的图像双重盲降噪算法。首先，使用改进的DnCNN模型作为CGAN的生成器来对加噪图片的噪声分布进行捕获；其次，将剔除噪声分布后的加噪图片和标签一同送入判别器进行降噪图像的判别；然后，利用判别结果对整个模型的隐层参数进行优化；最后，生成器和判别器在博弈中达到平衡，且生成器的残差捕获能力达到最优。实验结果表明，在Set12数据集上，当噪声水平分别为15、25、50时：所提算法与DnCNN算法相比，基于像素点间误差评价指标，其峰值信噪比（PSNR）值分别提升了1.388 dB、1.725 dB、1.639 dB；所提算法与三维块匹配（BM3D）、加权核范数最小化（WNNM）、DnCNN、收缩场级联（CSF）和一致性神经网络（CSNET）等现有算法相比，结构相似性（SSIM）评价指标值平均提升了0.000 2~0.104 1。实验结果验证了所提算法的优越性。

关键词: 图像双重盲降噪, 降噪卷积神经网络, 条件生成对抗网络, 生成器, 判别器

Abstract: In order to solve the problems of poor denoising effect and low computational efficiency in image denoising, a double blind denoising algorithm based on Denoising Convolutional Neural Network (DnCNN) and Conditional Generative Adversarial Net (CGAN) was proposed. Firstly, the improved DnCNN model was used as the CGAN generator to capture the noise distribution of the noisy image. Secondly, the noisy image after eliminating the noise distribution and the tag were sent to the discriminator to distinguish the noise reduction image. Thirdly, the results of discrimination were used to optimize the hidden layer parameters of the whole model. Finally, a balance between the generator and the discriminator was achieved in the game, and the generator's residual capture ability was optimal. Experimental results show that on Set12 dataset, when the noise levels are 15, 25, 50 respectively:compared with the DnCNN algorithm, the proposed algorithm has the Peak Signal-to-Noise Ratio (PSNR) increased by 1.388 dB, 1.725 dB and 1.639 dB respectively based on the error evaluation index between pixel points. Compared with the existing algorithms such as Block Matching 3D (BM3D), Weighted Nuclear Norm Minimization (WNNM), DnCNN, Cascade of Shrinkage Fields (CSF) and ConSensus neural NETwork (CSNET), the proposed algorithm has the index value of Structural SIMilarity (SSIM) improved by 0.000 2 to 0.104 1 on average based on the evaluation index of structural similarity. The above experimental results verify the superiority of the proposed algorithm.

Key words: image double blind denoising, Denoising Convolutional Neural Network (DnCNN), Conditional Generative Adversarial Net (CGAN), generator, discriminator

中图分类号:

TP391.41

井贝贝, 郭嘉, 王丽清, 陈静, 丁洪伟. 结合降噪卷积神经网络和条件生成对抗网络的图像双重盲降噪算法[J]. 计算机应用, 2021, 41(6): 1767-1774.

JING Beibei, GUO Jia, WANG Liqing, CHEN Jing, DING Hongwei. Image double blind denoising algorithm combining with denoising convolutional neural network and conditional generative adversarial net[J]. Journal of Computer Applications, 2021, 41(6): 1767-1774.

参考文献

[1] LI S Z. Markov Random Field Modeling in Image Analysis[M]. London:Springer,2009:49-86.
[2] ROTH S,BLACK M J. Fields of experts[J]. International Journal of Computer Vision,2009,82(2):Article No. 205.
[3] MAIRAL J,BACH F,PONCE J,et al. Non-local sparse models for image restoration[C]//Proceedings of the IEEE 12th International Conference on Computer Vision. Piscataway:IEEE,2009:2272-2279.
[4] XU J,ZHANG L,ZUO W,et al. Patch group based nonlocal selfsimilarity prior learning for image denoising[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway:IEEE,2015:244-252.
[5] SCHMIDT U, ROTH S. Shrinkage fields for effective image restoration[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2014:2774-2781.
[6] GU S, ZHANG L, ZUO W, et al. Weighted nuclear norm minimization with application to image denoising[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2014:2862-2869.
[7] DABOV K,FOI A,KATKOVNIK V,et al. Image denoising by sparse 3-D transform-domain collaborative filtering[J]. IEEE Transactions on Image Processing,2007,16(8):2080-2095.
[8] ZHANG K,ZUO W,CHEN Y,et al. Beyond a Gaussian denoiser:residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing,2017,26(7):3142-3155.
[9] CHEN Y,YU W,POCK T,et al. On learning optimized reaction diffusion processes for effective image restoration[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2015:5261-5269.
[10] CHEN Y,POCK T. Trainable nonlinear reaction diffusion:a flexible framework for fast and effective image restoration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(6):1256-1272.
[11] 徐少平, 林珍玉, 陈孝国, 等. 采用多通道浅层CNN网络构建的多降噪器最优组合模型[J/OL]. 自动化学报:1-16.[2020-08-12]. https://doi.org/10.16383/j.aas.c190736.(XU S P, LIN Z Y, CHEN X G,et al. Optimal combination model of multiple denoisers constructed by multi-channel shallow CNN network[J/OL]. Acta Automatica Sinica:1-16.[2020-08-12]. https://doi.org/10.16383/j.aas.c190736.)
[12] 陈清江, 石小涵, 柴昱洲. 基于小波变换与卷积神经网络的图像去噪算法[J]. 应用光学,2020,41(2):288-295.(CHEN Q J,SHI X H,CHAI Y Z. Image denoising algorithm based on wavelet transform and convolutional neural network[J]. Journal of Applied Optics,2020,41(2):288-295.)
[13] 潘凯, 侯亮. 基于卷积神经网络的遥感图像降噪[J]. 现代信息科技,2020,4(12):60-65.(PAN K,HOU L. Denoise of remote sensing image based on convolutional neural network[J]. Modern Information Technology,2020,4(12):60-65.)
[14] 杨飘. 基于区域分析的图像超分辨与降噪技术研究[D]. 成都:电子科技大学,2020:13-64.(YANG P. Research on image super-resolution and noise reduction technology based on area analysis[D]. Chengdu:University of Electronic Science and Technology of China,2020:13-64.)
[15] 朱小方, 净亮, 邵党国. 基于反向传播神经网络的自适应双边滤波的超声图像降噪[J]. 激光与光电子学进展, 2020, 57(24):163-172. (ZHU X F,JING L,SHAO D G. Ultrasonic image denoising using adaptive bilateral filtering based on back propagation neural network[J]. Laser and Optoelectronics Progress,2020,57(24):163-172.)
[16] ZHANG K,ZUO W,ZHANG L. FFDNet:toward a fast and flexible solution for CNN-based image denoising[J]. IEEE Transactions on Image Processing,2018,27(9):4608-4622.
[17] CHOI J H,OMAR A. Optimal combination of image denoisers[J]. IEEE Transactions on Image Processing,2019,28(8):4016-4031
[18] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2015:1-9.
[19] HEGAZY M A A,CHO M H,LEE S Y. Image denoising by transfer learning of generative adversarial network for dental CT[J]. Biomedical Physics and Engineering Express,2020,6(5):Article No. 055024.
[20] RADOSLAY L. CSNET[J]. Proceedings of FPCA,2012,7(7):429-462.
[21] 马红强, 马时平, 许悦雷, 等. 基于改进栈式稀疏去噪自编码器的自适应图像去噪[J]. 光学学报, 2018, 38(10):120-127. (MA H Q,MA S P,XU Y L, et al. Adaptive image denoising based on improved stacked sparse denoising auto-encoder[J]. Acta Optica Sinica,2018,38(10):120-127.)
[22] GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al. Generative adversarial nets[C]//Proceedings of the 2014 27th International Conference on Neural Information Processing Systems. Cambridge:MIT Press,2014:2672-2680.
[23] GAUTHIER J. Conditional generative adversarial nets for convolutional face generation[EB/OL].[2020-08-25]. http://www.foldl.me/uploads/papers/tr-cgans.pdf.
[24] 郭恒意, 贾振堂. 结合残差密集块的卷积神经网络图像去噪方法[J]. 计算机工程与设计, 2020, 41(7):1998-2003.(GUO H Y,JIA Z T. Convolutional neural network image denoising method combined with dense residual block[J]. Computer Engineering and Design,2020,41(7):1998-2003.)
[25] REDDI S J,KALE S,KUMAR S,et al. On the convergence of Adam and beyond[EB/OL].[2020-08-25]. https://arxiv.org/pdf/1904.09237.pdf.
[26] LUO L,XIONG Y,LIU Y,et al. Adaptive gradient methods with dynamic bound of learning rate[EB/OL].[2020-08-25]. https://arxiv.org/pdf/1902.09843.pdf.
[27] GOYAL P,DOLLÁR P,GIRSHICK R,et al. Accurate,large minibatch SGD:training ImageNet in 1 hour[EB/OL].[2020-08-26]. https://arxiv.org/pdf/1706.02677.pdf.
[28] KESKAR N S,MUDIGERE D,NOCEDAL J,et al. On largebatch training for deep learning:generalization gap and sharp minima[EB/OL].[2020-08-26]. https://arxiv.org/pdf/1609.04836.pdf.
[29] HOFFER E,HUBARA I,SOUDRY D. Train longer,generalize better:closing the generalization gap in large batch training of neural networks[C]//Proceedings of the 201731st International Conference on Neural Information Processing. Red Hook:Curran Associates Inc.,2017:1729-1739.
[30] LEVIN A,NADLER B. Natural image denoising:optimality and inherent bounds[C]//Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2011:2833-2840.
[31] LEVIN A,NADLER B,DURAND F,et al. Patch complexity, finite pixel correlations and optimal denoising[C]//Proceedings of the 2012 12th European Conference on Computer Vision,LNCS 7576. Berlin:Springer,2012:73-86.
[32] 王鸿南, 钟文, 汪静, 等. 图像清晰度评价方法研究[J]. 中国图象图形学报, 2004, 9(7):828-831.(WANG H N,ZHONG W, WANG J, et al. Research of measurement for digital image definition[J]. Journal of Image and Graphics,2004,9(7):828-831.)

结合降噪卷积神经网络和条件生成对抗网络的图像双重盲降噪算法

Image double blind denoising algorithm combining with denoising convolutional neural network and conditional generative adversarial net

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

[1]	郭茂祖, 杨倩楠, 赵玲玲. 基于条件Wassertein生成对抗网络的图像生成[J]. 计算机应用, 2021, 41(5): 1432-1437.
[2]	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.
[3]	王云飞, 王园宇. 基于Msmall-Patch训练的夜晚单幅图像去雾算法——MP-CGAN[J]. 计算机应用, 2020, 40(3): 865-871.
[4]	张泽林, 徐军. 基于条件生成对抗网络的乳腺上皮和间质区域自动分割[J]. 计算机应用, 2020, 40(10): 2910-2916.