首页 > 论文 > 光学学报 > 38卷 > 10期(pp:1010001--1)

基于改进栈式稀疏去噪自编码器的自适应图像去噪

Adaptive Image Denoising Based on Improved Stacked Sparse Denoising Auto-Encoder

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对栈式稀疏去噪自编码器(SSDA)在图像去噪上训练难度大、收敛速度慢和普适性差等问题,提出了一种基于栈式修正降噪自编码器的自适应图像去噪模型。采用线性修正单元作为网络激活函数,以缓解梯度弥散现象;借助残差学习和批归一化进行联合训练,加快收敛速度;而为克服新模型对噪声普适性差等问题,需要对其进行多通道并行训练,充分利用网络挖掘出的潜在数据特征集计算出最优通道权重,并通过训练权重权重预测模型预测出各通道最优权重,从而实现自适应图像去噪。实验结果表明:与目前降噪较好的BM3D和SSDA方法相比,所提方法不仅在收敛效果上优于SSDA方法,而且能够自适应处理未参与训练的噪声,使其具有更好的普适性。

Abstract

Aiming at the problems that the stacked sparse denoising auto-encoder(SSDA) is difficult to train on image denoising, such as slow convergence rate and poor universality, an adaptive image denoising model based on stacked rectified denoising auto-encoder is proposed. The rectified linear units is used as a network activation function to alleviate the phenomenon of gradient dispersion. Joint training with the residual learning and batch normalization to accelerate convergence speed. In order to solve the problem of noise poor universality of the new model, it is necessary to carry out the multi-channel parallel training, and make full use of the potential data feature extracted by the network to find the optimal channel weights, and learn to predict optimal column weights via training weight prediction model for realizing adaptive image denoising. The experimental results show that the proposed algorithm is not only better than the SSDA in the convergence effect, but also adaptively processing the non-participating training noise, and has better universality, compared with the current methods of BM3D and SSDA.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/aos201838.1010001

所属栏目:图像处理

基金项目:国家自然科学基金(61372167,61379104)

收稿日期:2018-03-06

修改稿日期:2018-04-14

网络出版日期:2018-05-08

作者单位    点击查看

马红强:中国人民解放军95876部队, 甘肃 山丹 734100
马时平:中国人民解放军95876部队, 甘肃 山丹 734100
许悦雷:中国人民解放军95876部队, 甘肃 山丹 734100
吕超:空军工程大学航空工程学院, 陕西 西安 710038
朱明明:中国人民解放军95876部队, 甘肃 山丹 734100

联系人作者:马红强(18049025189@163.com); 马时平(1402543131@qq.com);

【1】Meng Q K, He J,Qiu R C, et al. Crop recognition and navigation line detection in natural environment based on machine vision[J]. Acta Optica Sinica, 2014, 34(7): 0715002.
孟庆宽, 何洁, 仇瑞承, 等. 基于机器视觉的自然环境下作物行识别与导航线提取[J]. 光学学报, 2014, 34(7): 0715002.

【2】Tu S Q, Xue Y J, Liang Y, et al. Review on RGB-D image classification[J]. Laser & Optoelectronics Progress, 2016, 53(6): 060003.
涂淑琴, 薛月菊, 梁云, 等. RGB-D图像分类方法研究综述[J]. 激光与光电子学进展, 2016, 53(6): 060003.

【3】Yu L Q, Qin Y L, Zhang X S. Denoising of strong noisy image via gradient reweighted non-local averaging over learned dictionaries[J]. Laser & Optoelectronics Progress, 2016, 53(11): 111002.
余临倩, 覃亚丽, 张晓帅. 基于字典学习的梯度重权非局部平均的强噪声图像去噪[J]. 激光与光电子学进展, 2016, 53(11): 111002.

【4】Portilla J, Strela V, Wainwright M J, et al. Image denoising using scale mixtures of Gaussians in the wavelet domain[J]. IEEE Transactions on Image Processing, 2003, 12(11): 1338-1351.

【5】Yan X F, Yang B, Zhang W, et al. An improved denoising algorithm of feather and down image based on KSVD[C]∥Proceedings of IEEE International Conference on Information Technology in Medicine and Education, 2016: 419-423.

【6】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.

【7】Xu S P, Zhang X Q, Jiang Y N, et al. Noise level estimation based on local means and its application to the blind BM3D denoising algorithm[J]. Journal of Image and Graphics, 2017, 22(4): 422-434.
徐少平, 张兴强, 姜尹楠, 等. 局部均值噪声估计的盲3维滤波降噪算法[J]. 中国图象图形学报, 2017, 22(4): 422-434.

【8】Yu K, Jia L, Chen Y Q, et al. Deep learning: yesterday, today, and tomorrow[J]. Journal of Computer Research and Development, 2013, 50(9): 1799-1804.
余凯, 贾磊, 陈雨强, 等. 深度学习的昨天、今天和明天[J]. 计算机研究与发展, 2013, 50(9): 1799-1804.

【9】Harmeling S, Schuler C J, Burger H C. Image denoising: Can plain neural networks compete with BM3D?[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2012: 2392-2399.

【10】Xie J Y, Xu L L, Chen E H. Image denoising and inpainting with deep neural networks[C]∥Proceedings of the 25th International Conference on neural information processing systems, 2012: 341-349.

【11】Li H M. Deep learning for image denoising[J]. International Journal of Signal Processing, Image Processing and Pattern Recognition, 2014, 7(3): 171-180.

【12】Zhang Y G, Yi B S, Wu C Y, et al. Low-dose CT image denoising method based on convolutional neural network[J]. Acta Optica Sinica, 2018, 38(4): 0410003.
章云港, 易本顺, 吴晨玥, 等. 基于卷积神经网络的低剂量CT图像去噪方法[J]. 光学学报, 2018, 38(4): 0410003.

【13】Xu J, Xiang L, Liu Q S, et al. Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images[J]. IEEE Transactions on Medical Imaging, 2016, 35: 119-130.

【14】Glorot X, Bordes A, Bengio Y, et al. Deep sparse rectifier neural networks[J]. Journal of Machine Research, 2010: 315-323.

【15】Lu Y S, Li Y X, Liu B, et al. Hyperspectral data haze monitoring based on deep residual network[J]. Acta Optica Sinica, 2017, 37(11): 1128001.
陆永帅, 李元祥, 刘波, 等. 基于深度残差网络的高光谱遥感数据霾监测[J]. 光学学报, 2017, 37(11): 1128001.

【16】Zhu W, Qu J Y, Wu R B. Straight convolutional neural networks algorithm based on batch normalization for image classification[J]. Journal of Computer-Aided Design & Computer Graphics, 2017, 29(9): 1650-1657.
朱威, 屈景怡, 吴仁彪. 结合批归一化的直通卷积神经网络图像分类算法[J]. 计算机辅助设计与图形学学报, 2017, 29(9): 1650-1657.

【17】Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]∥Proceedings of 32nd International Conference on Machine Learning, 2015: 448-456.

【18】Gai J F, Zhao G R, Song C. Model predictive control based on linearization and neural network approach[J]. Systems Engineering and Electronics, 2015, 37(2): 394-399.
盖俊峰, 赵国荣, 宋超. 基于线性近似和神经网络逼近的模型预测控制[J]. 系统工程与电子技术, 2015, 37(2): 394-399.

【19】Zhang K, Zuo W M, Chen Y J, 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.

引用该论文

Ma Hongqiang,Ma Shiping,Xu Yuelei,Lü Chao,Zhu Mingming. Adaptive Image Denoising Based on Improved Stacked Sparse Denoising Auto-Encoder[J]. Acta Optica Sinica, 2018, 38(10): 1010001

马红强,马时平,许悦雷,吕超,朱明明. 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): 1010001

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF