基于局部路径特征信息神经网络的图像去噪

王慧; 冯金顺; 程正兴

doi:10.3788/YJYXS20203501.0070

您当前的位置：

首页 >

文章列表页 >

基于局部路径特征信息神经网络的图像去噪

图像处理 | 更新时间：2020-07-05

- 基于局部路径特征信息神经网络的图像去噪
- Image denoising based on local path feature in formation neural network
- 液晶与显示 2020年35卷第1期页码：70-79
- 作者机构：
  
  1.南阳理工学院师范学院, 河南南阳 473000
  2.西安交通大学数学与统计学院, 陕西西安 710049
- 作者简介：
  
  [ "王慧(1972-), 女, 河南南阳人, 硕士, 副教授, 2009年于河南师范大学获得硕士学位, 主要从事图像处理方面的研究。E-mail:whmrfw@126.com" ]
  冯金顺(1962-), 男, 河南南阳人, 教授, 1988年于信阳师范学院获得学士学位, 主要从事函数论及其应用的研究。E-mail:nyfjs@163.com
- 基金信息：
- DOI：10.3788/YJYXS20203501.0070
  中图分类号： TP391.4
- 收稿日期：2019-05-09，
  
  修回日期：2019-10-27，
  
  录用日期：2019-10-27，
  
  纸质出版日期：2020-01-05
- 稿件说明：
移动端阅览
王慧, 冯金顺, 程正兴. 基于局部路径特征信息神经网络的图像去噪[J]. 液晶与显示, 2020,35(1):70-79.

Hui WANG, Jin-shun FENG, Zhen-xing CHENG. Image denoising based on local path feature in formation neural network[J]. Chinese journal of liquid crystals and displays, 2020, 35(1): 70-79.
王慧, 冯金顺, 程正兴. 基于局部路径特征信息神经网络的图像去噪[J]. 液晶与显示, 2020,35(1):70-79. DOI： 10.3788/YJYXS20203501.0070.

Hui WANG, Jin-shun FENG, Zhen-xing CHENG. Image denoising based on local path feature in formation neural network[J]. Chinese journal of liquid crystals and displays, 2020, 35(1): 70-79. DOI： 10.3788/YJYXS20203501.0070.

摘要

图像去噪旨在减少或消除噪声对图像的影响，这一过程往往会有高频细节信息的丢失。为了在去除图像噪声的同时保护图像的边缘信息与纹理细节，本文提出了一种能够连接图像局部路径信息的神经网络，该网络训练完成后可以直接对含噪声图像进行降噪，不需要对图像进行预处理。本文提出的神经网络包括3个部分：特征提取层、信息连接模块、信息重建层。信息连接模块是该网络的关键部分，通过残差学习连接局部长路径和局部短路径的特征信息。实验结果表明，经本文处理后的图像在有参考的图像质量评价指标PSNR和SSIM上均有明显提升，PSNR最高可以达到34.87 dB，SSIM可以达到0.87以上；在无参考的图像质量评价指标BRISQUE和NIQE上均有明显下降。本文算法对不同水平、不同种类的算法都有相对较好的效果，且性能优于一般算法，在去噪工作中有一定的实用价值。

Abstract

Image denoising aims to reduce or eliminate the effects of noise on images. This process often has the loss of high frequency information. In order to protect the edge information and texture details of the image while removing image noise

a convolution neural network which can connect image local path information is proposed. After training

the network can directly denoise the noisy image without preprocessing the image. The neural network proposed in this paper consists of three parts

feature extraction layer

information connection blocks and information reconstruction layer. The information connection blocks are key part of the network

and the mixed feature information of the local long path and the local short path is extracted through residual learning. The experimental results show that the image processed by this algorithm has a significant improvement on the reference image quality evaluation index PSNR and SSIM

the maximum PSNR can reach 34.87 dB

SSIM can reach more than 0.87

and the image quality evaluation index BRISQUE and NIQE without reference have a significant decline. The algorithm in this paper has a relatively good effect on different levels and different kinds of algorithms

and its performance is better than the general algorithm. It has a certain practical value in denoising work.

关键词

Keywords

references

BUADES A, COLL B, MOREL J M. A non-local algorithm for image denoising[C]// Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . San Diego, CA, USA: IEEE, 2005: 60-65.

HE K M, SUN J, TANG X O. Guided image filtering[C]// Proceedings of the 11 th European Conference on Computer Vision . Heraklion, Crete, Greece: Springer, 2010: 1-14.

L SENDUR , I W SELESNICK . Bivariate shrinkage functions for wavelet-based denoising exploiting interscale dependency . IEEE Transactions on Signal Processing , 2002 . 50 ( 11 ): 2744 - 2756 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=bd004ce56c79633859e1edec27efe212 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=bd004ce56c79633859e1edec27efe212 .

E YAHAGHI , A MOVAFEGHI . Contrast enhancement of industrial radiography images by Gabor filtering with automatic noise Thresholding . Russian Journal of Nondestructive Testing , 2019 . 55 ( 1 ): 73 - 79 . http://cn.bing.com/academic/profile?id=017b8fe67ac67f7b26e9e208bd7bdc2c&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=017b8fe67ac67f7b26e9e208bd7bdc2c&encoded=0&v=paper_preview&mkt=zh-cn .

王珺楠 , 邱欢 , 张丽娟 , 等 . 基于小波域Curvelet变换的湍流图像去噪算法 . 液晶与显示 , 2017 . 32 ( 11 ): 905 - 913 . http://yjyxs.com/CN/abstract/abstract10246.shtml http://yjyxs.com/CN/abstract/abstract10246.shtml .

J N WANG , H QIU , L J ZHANG , 等 . Atmospheric turbulence image denoising algorithm based on wavelet-domain curvelet transform . Chinese Journal of Liquid Crystals and Displays , 2017 . 32 ( 11 ): 905 - 913 . http://yjyxs.com/CN/abstract/abstract10246.shtml http://yjyxs.com/CN/abstract/abstract10246.shtml .

B Y CHEN , X FENG , R H WU , 等 . Adaptive wavelet filter with edge compensation for remote sensing image denoising . IEEE Access , 2019 . 7 91966 - 91979 . http://cn.bing.com/academic/profile?id=7e10fc3c7929dfd02116e4f4ef840de5&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=7e10fc3c7929dfd02116e4f4ef840de5&encoded=0&v=paper_preview&mkt=zh-cn .

M AHARON , M ELAD , A BRUCKSTEIN . K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation . IEEE Transactions on Signal Processing , 2006 . 54 ( 11 ): 4311 - 4322 . http://d.old.wanfangdata.com.cn/Periodical/dndxxb201106002 http://d.old.wanfangdata.com.cn/Periodical/dndxxb201106002 .

W S DONG , L ZHANG , G M SHI , 等 . Nonlocally centralized sparse representation for image restoration . IEEE Transactions on Image Processing , 2013 . 22 ( 4 ): 1620 - 1630 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=CC0214625132 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=CC0214625132 .

焦莉娟 , 王文剑 , 赵青杉 , 等 . 近邻局部OMP稀疏表示图像去噪 . 中国图象图形学报 , 2017 . 22 ( 11 ): 1486 - 1492 . http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201711002 http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201711002 .

L J JIAO , W J WANG , Q S ZHAO , 等 . Image denoising based on sparse representation of neighbor local OMP . Journal of Image and Graphics , 2017 . 22 ( 11 ): 1486 - 1492 . http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201711002 http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201711002 .

GU S S, ZHANG L, ZUO W M, et al . Weighted nuclear norm minimization with application to Image denoising[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition . Columbus, OH, USA: IEEE, 2014: 2862-2869.

K DABOV , A FOI , V KATKOVNIK , 等 . Image denoising by sparse 3-D transform-domain collaborative filtering . IEEE Transactions on Image Processing , 2007 . 16 ( 8 ): 2080 - 2095 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=b6a4298d9aee3a49073c79b010dd5b2a http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=b6a4298d9aee3a49073c79b010dd5b2a .

M BANSAL , M DEVI , N JAIN , 等 . A proposed approach for biomedical image denoising using PCA_NLM . International Journal of Bio-Science and Bio-Technology , 2014 . 6 ( 6 ): 13 - 20 .

ZORAN D, WEISS Y. From learning models of natural image patches to whole image restoration[C]// Proceedings of 2011 International Conference on Computer Vision . Barcelona, Spain: IEEE, 2011: 479-486.

方杰 , 韦穗 , 苏守宝 . 基于整体变分降噪算法下的多频率超声衍射层析成像 . 电子学报 , 2009 . 37 ( 4 ): 828 - 832 . http://d.old.wanfangdata.com.cn/Periodical/dianzixb200904028 http://d.old.wanfangdata.com.cn/Periodical/dianzixb200904028 .

J FANG , S WEI , S B SU . The multi-band diffraction ultrasound tomography images based on the total variation denoised algorithm . Acta Electronica Sinica , 2009 . 37 ( 4 ): 828 - 832 . http://d.old.wanfangdata.com.cn/Periodical/dianzixb200904028 http://d.old.wanfangdata.com.cn/Periodical/dianzixb200904028 .

Q CHEN , P MONTESINOS , Q S SUN , 等 . Adaptive total variation denoising based on difference curvature . Image and Vision Computing , 2010 . 28 ( 3 ): 298 - 306 . http://cn.bing.com/academic/profile?id=7f64dba1e507f30c88bebeb36c91b717&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=7f64dba1e507f30c88bebeb36c91b717&encoded=0&v=paper_preview&mkt=zh-cn .

A KUMAR , M O AHMAD , M N S SWAMY . Tchebichef and adaptive steerable-based total variation model for image denoising . IEEE Transactions on Image Processing , 2019 . 28 ( 6 ): 2921 - 2935 . http://cn.bing.com/academic/profile?id=3827453109abf56828c3ddb63a54dd79&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=3827453109abf56828c3ddb63a54dd79&encoded=0&v=paper_preview&mkt=zh-cn .

刘小晴 , 左清曈 , 刘青 , 等 . 超低信噪比冷冻电镜图像的深度学习去噪算法-DWT-CAE . 小型微型计算机系统 , 2019 . 40 ( 6 ): 1340 - 1345 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xxwxjsjxt201906037 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xxwxjsjxt201906037 .

X Q LIU , Q T ZUO , Q LIU , 等 . Noise reduction algorithm on the extremely low signal-noise ratio CryoEM images based on deep learning Methods-DWT-CAE . Journal of Chinese Computer Systems , 2019 . 40 ( 6 ): 1340 - 1345 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xxwxjsjxt201906037 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xxwxjsjxt201906037 .

赖睿 , 官俊涛 , 徐昆然 , 等 . 级联残差学习的红外图像非均匀性校正方法 . 西安电子科技大学学报 , 2019 . 46 ( 1 ): 14 - 19 . http://d.old.wanfangdata.com.cn/Periodical/xadzkjdx201901003 http://d.old.wanfangdata.com.cn/Periodical/xadzkjdx201901003 .

R LAI , J T GUAN , K R XU , 等 . Cascade residual learning method for infrared image nonuniformity correction . Journal of Xidian University , 2019 . 46 ( 1 ): 14 - 19 . http://d.old.wanfangdata.com.cn/Periodical/xadzkjdx201901003 http://d.old.wanfangdata.com.cn/Periodical/xadzkjdx201901003 .

K ZHANG , W M ZUO , Y J CHEN , 等 . Beyond a gaussian denoiser:residual learning of deep CNN for image denoising . IEEE Transactions on Image Processing , 2017 . 26 ( 7 ): 3142 - 3155 . http://cn.bing.com/academic/profile?id=c6b2b5f8ac0103b83ba54a3d9faa4283&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=c6b2b5f8ac0103b83ba54a3d9faa4283&encoded=0&v=paper_preview&mkt=zh-cn .

ALJADAANY R, PAL D K, SAVVIDES M. Proximal splitting networks for image restoration[C]// Proceedings of the 16 th International Conference on Image Analysis and Recognition . Waterloo, Canada: Springer, 2019: 3-17.

吴从中 , 陈曦 , 季栋 , 等 . 结合深度残差学习和感知损失的图像去噪 . 中国图象图形学报 , 2018 . 23 ( 10 ): 1483 - 1491 . http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201810004 http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201810004 .

C Z WU , X CHEN , D JI , 等 . Image denoising via residual network based on perceptual loss . Journal of Image and Graphics , 2018 . 23 ( 10 ): 1483 - 1491 . http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201810004 http://d.old.wanfangdata.com.cn/Periodical/zgtxtxxb-a201810004 .

F ZHANG , N CAI , J X WU , 等 . Image denoising method based on a deep convolution neural network . IET Image Processing , 2018 . 12 ( 4 ): 485 - 493 . https://ieeexplore.ieee.org/document/8320125 https://ieeexplore.ieee.org/document/8320125 .

ZHAO D, MA L, LI S N, et al . End-to-End denoising of dark burst images using recurrent fully convolutional networks[J]. arXiv: 1904.07483, 2019.

D R MARTIN , C C FOWLKES , J MALIK . Learning to detect natural image boundaries using local brightness, color, and texture cues . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2004 . 26 ( 5 ): 530 - 549 . http://d.old.wanfangdata.com.cn/NSTLQK/10.1109-TPAMI.2004.1273918/ http://d.old.wanfangdata.com.cn/NSTLQK/10.1109-TPAMI.2004.1273918/ .

M BEVILACQUA , A ROUMY , C GUILLEMOT , 等 . Single-image super-resolution via linear mapping of interpolated self-examples . IEEE Transactions on Image Processing , 2014 . 23 ( 12 ): 5334 - 5347 . https://www.ncbi.nlm.nih.gov/pubmed/25347880 https://www.ncbi.nlm.nih.gov/pubmed/25347880 .

K ZHANG , X GAO , D TAO , 等 . Single image super-resolution with non-local means and steering kernel regression . IEEE Transactions on Image Processing , 2012 . 21 ( 11 ): 4544 - 4556 . http://cn.bing.com/academic/profile?id=b9f503a9d219d34b21812e2ee89aa4d6&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=b9f503a9d219d34b21812e2ee89aa4d6&encoded=0&v=paper_preview&mkt=zh-cn .

A MITTAL , A K MOORTHY , A C BOVIK . No-reference image quality assessment in the spatial domain . IEEE Transactions on Image Processing , 2012 . 21 ( 12 ): 4695 - 4708 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=3f22d9820e6638ca4b6355a9f1d634bc http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=3f22d9820e6638ca4b6355a9f1d634bc .

A MITTAL , J SOUNDARARAJAN , A C BOVIK . Making a "completely blind" image quality analyzer . IEEE Signal Processing Letters , 2013 . 20 ( 3 ): 209 - 212 . http://cn.bing.com/academic/profile?id=8170c1f2e24ff67a023446dc1c7c10a8&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=8170c1f2e24ff67a023446dc1c7c10a8&encoded=0&v=paper_preview&mkt=zh-cn .

XU J, ZHANG L, ZHANG D. A trilateral weighted sparse coding scheme for real-world image denoising[C]// Proceedings of the 15 th European Conference on Computer Vision . Munich, Germany: Springer, 2018: 21-38.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于CNN的异构FPGA硬件加速器设计

残差学习与层注意力相结合的轻量级图像超分辨

基于CNN-Transformer结构的遥感影像变化检测

基于P-U-net的角锥波前探测器的波前校正方法

基于多级联递进卷积结构的图像去雨算法