加权密集扩张卷积网络的随机脉冲噪声去除

doi:10.3778/j.issn.1002-8331.2205-0204

摘要/Abstract

摘要： 基于深度学习的图像去噪方法，大多没有充分利用不同层次的特征信息，通道合并时都是直接在通道维度上对特征图进行拼接，并没有考虑到浅层与深层卷积特征各自的重要性。为解决上述问题，提出一种加权密集扩张卷积连接网络模型，用于去除图像的随机脉冲噪声。通过使用不同扩张因子的扩张卷积来丰富浅层特征图的多尺度特征信息;考虑到浅层与深层卷积特征各自的重要性，将原始密集块进行改进，采用加权密集连接结构，并使用扩张卷积提高感受野;采用跳跃连接，将浅层的多尺度特征信息和不同加权密集扩张卷积块的特征信息进行融合，充分利用深层卷积特征和浅层卷积特征信息实现随机脉冲噪声的复原。实验结果表明，所提模型的去噪效果更加突出。

关键词: 图像去噪, 深度学习, 密集连接, 扩张卷积, 权重, 随机脉冲噪声

Abstract: Among image denoising methods based on deep learning, most of them do not make full use of feature information at different levels, and splicing feature graphs directly on channel dimensions during channel merging, without considering the importance of both shallow and deep convolution features. In order to solve the above problems, this paper proposes a weighted dense dilated convolutional connection network to remove random impulse noise in images. Firstly, the multi-scale feature information of the shallow feature map is enriched by dilation convolution using different expansion factors. Secondly, considering the importance of both shallow and deep convolution features, the original dense block is improved, the weighted dense connection structure is adopted, and the expansion convolution is used to effectively increase the receptive field. Finally, jump connections are used to fuse the shallow multi-scale feature information with the feature information of different weighted dense dilated convolution blocks, and make full use of the high-level and low-level feature information to recover random impulse noise. The experimental results show that the proposed algorithm has a more prominent denoising.

Key words: image denoising, deep learning, dense connection, dilated convolution, weight, random impulsive noise

曹义亲, 符杨逸, 饶哲初. 加权密集扩张卷积网络的随机脉冲噪声去除[J]. 计算机工程与应用, 2023, 59(18): 179-189.

CAO Yiqin, FU Yangyi, RAO Zhechu. Weighted Dense Dilated Convolutional Network for Random Impulse Noise Removal[J]. Computer Engineering and Applications, 2023, 59(18): 179-189.

参考文献

[1] BONCELET C.Image noise models[M]//The essential guide to image processing.[S.l.]：Academic Press，2009：143-167.
[2] FARAJI H，MACLEAN W.CCD noise removal in digital images[J].IEEE Transactions on Image Processing，2006，15：2676-2685.
[3] LIU C，SZELISKI R，KANG B，et al.Automatic estimation and removal of noise from a single image[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2008，30：299-314.
[4] SMOLKA B，MALIK K，MALIK D.Adaptive rank weighted switching filter for impulsive noise removal in color images[J].Real-Time Image Processing，2012，10：289-311.
[5] MALINSKI L，SMOLKA B.Self-tuning fast adaptive algorithm for impulsive noise suppression in color images[J].Real-Time Image Processing，2020，17：1067-1087.
[6] NADEEM M，HUSSAIN A，MUNIR A，et al.Removal of random valued impulse noise from grayscale images using quadrant based spatially adaptive fuzzy filter[J].Signal Processing，2020，169：107403.
[7] DONG Y，CHAN R H，XU S.A detection statistic for random-valued impulse noise[J].IEEE Transactions on Image Processing，2007，16（4）：1112-1120.
[8] LYU Q，GUO M，PEI Z.DeGAN：mixed noise removal via generative adversarial networks[J].Applied Soft Computing，2020，95：106478.
[9] JIN K H，YE J C.Sparse and low-rank decomposition of a hankel structured matrix for impulse noise removal[J].IEEE Transactions on Image Processing，2018，27（3）：1448-1461.
[10] XU Q，LI Y H，GUO Y J，et al.Random-valued impulse noise removal using adaptive ranked-ordered impulse detector[J].Journal of Electronic Imaging，2018，27（1）：013001.
[11] MAFI M，RAJAEI H，CABRERIZO M，et al.A robust edge detection approach in the presence of high impulse noise intensity through switching adaptive median and fixed weighted mean filtering[J].IEEE Transactions on Image Processing，2018，27（11）：5475-5490.
[12] ROY A，SINGHA J，MANAM L，et al.Combination of adaptive vector median filter and weighted mean filter for removal of high-density impulse noise from color images[J].IEEE Transactions on Image Processing，2017，11（6）：352-361.
[13] WANGAC Y，FUB J，ADHAMIA R，et al.A novel learning-based switching median filter for suppression of impulse noise in highly corrupted color image[J].The Imaging Science Journal，2016，64（1）：15-25.
[14] MALINSKI L，SMOLKA B.Fast adaptive switching technique of impulsive noise removal in color images[J].Real-Time Image Processing，2019，16：1077-1098.
[15] 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，2017，26：3142-3155.
[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] GUO S，YAN Z F，ZHANG K，et al.Toward convolutional blind denoising of real photographs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2019：1712-1722.
[18] JIN L H，ZHANG W H，MA G Z，et al.Learning deep CNNs for impulse noise removal in images[J].Journal of Visual Communication and Image Representation，2019，62：193-205.
[19] ZHANG W H，JIN L H，SONG E，et al.Removal of impulse noise in color images based on convolutional neural network[J].Applied Soft Computing，2019，82（105558）：1-11.
[20] RADLAK K，MALINSKI L，SMOLKA B.Deep learning based switching filter for impulsive removal in color images[J].Sensors，2020，20（10）：2782.
[21] ZHAO Y Y，JIANG Z Q，MEN A D，et al.Pyramid real image denoising network[J].arXiv：1908.00273，2019.
[22] TIAN C，XU Y，LI Z，et al.Attention-guided CNN for image denoising[J].Neural Networks，2020，124：117-129.
[23] YU K，WANG X，DONG C，et al.Path-restore：learning network path selection for image restoration[J].arXiv：1904.
10343，2019.
[24] LI X，WANG W H，HU X L，et al.Selective kernel networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2019：510-519.
[25] HE K M，ZHANG X Y，REN S Q，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，Las Vegas，June 26-July 1，2016.Piscataway：IEEE，2016：770-778.
[26] YU F，KOLTUN V.Multi-scale context aggregation by dilated convolutions[C]//Proceedings of the International Conference on Learning Representations（ICLR），2016.
[27] HUANG G，LIU Z.Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017：2261-2269.
[28] LI H，XU Z，TAYLOR G，et al.Visualizing the loss landscape of neural nets[C]//Proceedings of the Conference and Workshop on Neural Information Processing Systems（NIPS），Montreal，Canada，2018：6389-6399.
[29] PASZKE A，GROSS S，MASSA F，et al.Pytorch：an imperative style，high-performance deep learning library[C]//Advances in Neural Information Processing Systems，Vancouber，Conada，2019：8024-8035.
[30] KINGMA D P，BA J.Adam：a method for stochastic optimization[J].arXiv：1412.6980，2014.
[31] ARBELAEZ P，MAIRE M，FOWLKES C，et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2010，33（5）：898-916.
[32] MARTIN D，FOWLKES C，TAL D，et al.A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]//Proceedings of the IEEE International Conference on Computer Vision（ICCV 2001），2001：416-423.
[33] ZORAN D，WEISS Y.From learning models of natural image patches to whole image restoration[C]//Proceedings of the IEEE International Conference on Computer Vision，2011：479-486.
[34] FRANZEN R.Kodak lossless true color image suite[EB/OL].（1999）.http：//r0k.us/graphics/kodak，1999.
[35] LI X，GUNTURK B，ZHANG L.Image demosaicing：a systematic survey[C]//Proceedings Volume 6822：Visual Communications and Image Processing，2008.
[36] XU J，LI H，LIANG Z，et al.Real-world noisy image denoising：a new benchmark[J].arXiv：1804.02603，2018.
[37] ZHANG Lin，ZHANG Lu，MOU X Q，et al.FSIM：a feature similarity index for image quality assessment[J].IEEE Transactions on Image Processing，2011，20（8）：2378-2386.
[38] ASTOLA J，HAAVISTO P，NEUVO Y.Vector median filters[J].Proceedings of the IEEE，1990，78（4）：678-689.
[39] CLELEBI M E，ASLANDOGAN Y A.Robust switching vector median filter for impulsive noise removal[J].Journal of Electronic Imaging，2008，17（4）：043006.
[40] SMOLKA B，CHYDZINSKI A.Fast detection and impulsive noise removal in color images[J].Real-Time Imaging，2005，11（5/6）：389-402.
[41] XU J，WANG L，SHI Z.A switching weighted vector median filter based on edges detection[J].Signal Processing，2014，98：359-369.
[42] YUAN G，GHANEM B.10tv：a new method for image restoration in the presence of impulse noise[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），Boston，MA，USA，2015：5369-5377.
[43] JIN L，ZHU Z，SONG E，et al.An effective vector filter for impulse noise reduction based on adaptive quaternion color distance mechanism[J].Singal Processing，2019，155：334-345.
[44] WANG G，LIU Y，ZHAO T.A quaternion-based switching filter for color image denoising[J].Signal Processing，2014，102：216-225.
[45] CAO Y Q，FU Y Y，ZHU Z L，et al.Color random valued impulse noise removal based on quaternion convolutional attention denoising network[J].Signal Processing Letters，2021，29：369-373.
[46] SEKVARAJU R R，COGSWELL M，DAS A，et al.Grad-cam：visual explanations from deep networks via gradient-based locational[C]//Proceedings of the IEEE International Conference on Computer Vision，Venice，October 22-29，2017.Berlin，Heidelberg：Springer，2017：618-626.