计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (6A): 230400073-7.doi: 10.11896/jsjkx.230400073

• 图像处理&多媒体技术 • 上一篇    下一篇

基于残差密集卷积自编码的高噪声图像去噪方法

张杰1, 卢淼鑫1, 李嘉康2, 徐大勇2, 黄雯潇1, 史小平3   

  1. 1 郑州轻工业大学电气信息工程学院 郑州 450002
    2 中国烟草总公司郑州烟草研究院烟草工艺重点实验室 郑州 450000
    3 哈尔滨工业大学控制与仿真中心 哈尔滨 150080
  • 发布日期:2024-06-06
  • 通讯作者: 徐大勇(396200648@qq.com)
  • 作者简介:(2018007@zzuli.edu.cn)
  • 基金资助:
    家自然科学基金(62102373,62006213);河南省科技攻关项目(222102320321,232102220020)

Residual Dense Convolutional Autoencoder for High Noise Image Denoising

ZHANG Jie1, LU Miaoxin1, LI Jiakang2, XU Dayong2, HUANG Wenxiao1, SHI Xiaoping3   

  1. 1 College of Electrical and Information Engineering,Zhengzhou University of Light Industry,Zhengzhou 450002,China
    2 Key Lab of Tobacco Technology,Zhengzhou Tobacco Research Institute of CNTC,Zhengzhou 450000,China
    3 Control and Simulation Center,Harbin Institute of Technology,Harbin 150080,China
  • Published:2024-06-06
  • About author:ZHANG Jie,born in 1986,Ph.D,lectu-rer.His main research interests include image denoising and deep learning.
    XU Dayong,born in 1982,master,senior engineer.His main research interests include bacco processing technology and hyperspectral image processing.
  • Supported by:
    National Natural Science Foundation of China(62102373,62006213) and Henan Province Science and Technology Research Project(222102320321,232102220020).

PDF (PC)

287

摘要： 在高噪声图像去噪中,传统卷积自编码器难以挖掘有效的深度特征信息,进而影响了图像的重建质量。为了提高高噪声图像的重建质量,提出了一种残差密集卷积自编码器网络模型。该模型首先使用卷积操作代替池化操作以提高高噪声图像的表征能力;同时,在编码和解码阶段设计三级密集残差网络结构,实现图像特征的有效挖掘;最后,设计一个优化损失函数以进一步提高重建图像的质量。实验结果表明,设计的去噪方法能够从高噪声图像中重建高质量的图像,同时能够保留更多的细节特征信息,有效验证了该算法在图像去噪中的有效性。该方法能够有效解决高噪声图像的去噪问题,具有重要的应用价值。

关键词: 图像去噪, 卷积自编码器, 残差密集卷积, 高噪声图像, 优化损失函数

Abstract: In the field of high noise image denoising,traditional convolutional auto-encoders face challenges in extracting meaningful depth feature information,resulting in poor image reconstruction quality.To address this issue and improve the reconstruction quality of high noise images,this paper proposes a residual-density convolutional auto-encoder network model.The model firstly uses convolutional operations instead of pooling operations to improve the characterisation of high noise images.Moreover,a three-stage dense residual network structure is designed for effective image feature mining during the coding and decoding stages.Finally,an optimised loss function is designed to further improve the quality of the reconstructed images.Experimental results show that the denoising method presented in this paper is capable of reconstructing high quality images from high noise images while preserving more detailed feature information.It confirms the effectiveness of the algorithm in image denoising.The proposed method effectively addresses the challenge of denoising high noise images and has significant practical value.

Key words: Image denoising, Convolutional autoencoder, Residual dense convolution, High noise image, Optimized loss function

中图分类号: 

  • TN911.73
[1]LIU D,JIA J L,ZHAO Y Q,et al.Overview of Image Denoising Methods Based on Deep Learning[J].Computer Engineering and Applications,2021,57(7):1-13.
[2]BUADES A,COLL B,MORELJ M.A non-local agorithm for image denoising[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’05).IEEE,2005:60-65.
[3]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.
[4]GU S,ZHANG L,ZUO W,et al.Weighted nuclear norm minimization with application to image denoising[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2014:2862-2869.
[5]GONDARA L.Medical image denoising using convolutional denoising autoencoders[C]//2016 IEEE 16th International Conference on Data Mining Workshops(ICDMW).IEEE,2016:241-246.
[6]ZHANG K,ZUO W,CHEN Y,et al.Beyond a gaussian denoi-ser:Residual learning of deep cnn for image denoising[J].IEEE Transactions on Image Processing,2017,26(7):3142-3155.
[7]ZHANG K,ZUO W,ZHANG L.FFDNet:Toward a fast andflexible solution for CNN-based image denoising[J].IEEE Transactions on Image Processing,2018,27(9):4608-4622.
[8]LUO R Z,WANG R J,ZHANG K,et al.Image Denoising Methodof Residual Convolution Auto-Encoder Network[J].Computer Simulation,2021,38(5):455-461.
[9]LEI J S,YAN C Y,YANG Z G.Convolutional Auto-Encoder for Image Denoising Based on Inception Model[J].Computer Applications and Software,2021,38(2):221-226,322.
[10]MA Z P,TAN L D.Blind Image Denoising Method Based onWavelet Autoencoder[J/OL].Journal of Huazhong University of Science and Technology(Natural Science Edition).(2022-12-14)[2023-06-25].https://doi.org/10.13245/j.hust.240208.
[11]YIN H T,WANG T Y.Image Denoising Algorithm Based on Deep Multi-scale Convolution Sparse Coding[J].Computer Science,2023,50(4):133-140.
[12]MAJUMDAR A.Blind denoising autoencoder[J].IEEE Transactions on Neural Networks and Learning Systems,2018,30(1):312-317.
[13]HUANG G,LIU Z,VAN DER MAATEN L,et al.Densely con-nected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:4700-4708.
[14]ZHANG Y,TIAN Y,KONGY,et al.Residual dense network for image restoration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,43(7):2480-2495.
[15]LU Y.The level weighted structural similarity loss:A step away from MSE[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019,33(1):9989-9990.
[16]SNELL J,RIDGEWAY K,LIAO R,et al.Learning to generate images with perceptual similarity metrics[C]//2017 IEEE International Conference on Image Processing(ICIP).IEEE,2017:4277-4281.
[17]ZHAO H,GALLO O,FROSIO I,et al.Loss functions for image restoration with neural networks[J].IEEE Transactions on Computational Lmaging,2016,3(1):47-57.
[18]IOFFE S,SZEGEDY C.Batch normalization:Accelerating deep network training by reducing internal covariate shift[C]//International Conference on Machine Learning.PMLR,2015:448-456.
[19]MA K,DUANMU Z,WU Q,et al.Waterloo exploration database:New challenges for image quality assessment models[J].IEEE Transactions on Image Processing,2016,26(2):1004-1016.
[20]TIAN C,XU Y,LI Z,et al.Attention-guided CNN for image denoising[J].Neural Networks,2020,124:117-129.
[21]MAIRAL J,BACH F,PONCE J,et al.Non-local sparse models for image restoration[C]//2009 IEEE 12th International Conference on Computer Vision.IEEE,2009:2272-2279.
[22]ROTH S,BLACK M J.Fields of experts:A framework forlearning image priors[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’05).IEEE,2002:860-867.
[23]SARA U,AKTER M,UDDINM S.Image quality assessment through FSIM,SSIM,MSE and PSNR－a comparative study[J].Journal of Computer and Communications,2019,7(3):8-18.
[24]TOMASI C,MANDUCHI R.Bilateral filtering for gray and color images[C]//Sixth International Conference on Computer Vision(IEEE Cat.No.98CH36271).IEEE,1998:839-846.
[25]LIU P,ZHANG H,ZHANG K,et al.Multi-level wavelet-CNN for image restoration[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops.2018:773-782.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发