期刊文献+

基于非对称卷积神经网络的图像去噪 被引量:4

Image Denoising Based on Asymmetric Convolutional Neural Networks
原文传递
导出
摘要 由于图像的像素越来越小,数字成像传感器输出的信号对光子噪声的敏感性越来越强,使光子噪声成为数字图像传感器噪声的主要来源。鉴于此,提出一种基于非对称卷积神经网络的图像去噪算法。为了提高模型的泛化能力,将网络框架分为噪声评估网络和去噪网络两部分。为了减少编码器与解码器中网络特征映射之间的语义差距,对去噪网络中的跳跃连接进行改进,使特征在语义上更相似,以便于任务的优化处理。从定性和定量方面进行对比实验,实验结果表明,改进后的网络模型的去噪性能更佳。 Owing to the continuing decrement in the pixels of the images,the signal output of the digital imaging sensor is increasingly sensitive to photon noise,making the photon noise the main source of noise in the digital image sensor.To address this issue,an image denoising algorithm based on asymmetric convolutional neural networks is proposed herein.To enhance the generalization ability of the model,the network framework is divided into two parts:noise evaluation network and denoising network.To reduce the semantic gap between the network feature mapping in the encoder and the decoder,the skip connection in the denoising network is improved to make the features more similar in semantics to facilitate task optimization.From the qualitative and quantitative aspects of comparative experiments,the experimental results show that the proposed network model exhibits better denoising performance.
作者 甘建旺 沙芸 张国英 Gan Jianwang;Sha Yun;Zhang Guoying(School of Information Engineering,Beijing Institute of Petrochemical Technology,Beijing 102617,China;School of Mechanical Electronic&Information Engineering,China University of Mining and Techologyg(Beijing),Beijing 100083,China)
出处 《激光与光电子学进展》 CSCD 北大核心 2020年第22期193-198,共6页 Laser & Optoelectronics Progress
关键词 图像处理 非对称卷积神经网络 去噪 跳跃连接 光子噪声 image processing asymmetric convolutional neural network denoising skip connection photon noise
  • 相关文献

参考文献1

二级参考文献10

  • 1佟雨兵,胡薇薇,杨东凯,张其善.视频质量评价方法综述[J].计算机辅助设计与图形学学报,2006,18(5):735-741. 被引量:47
  • 2Daly S.The visible difference predictor:an algorithm for the assessment of image fidelity,digital images and human vision[M].Massachusetts,U S A:The MIT Press,1993:179 -206
  • 3Heeger D J,Teo T C.A model of perceptual image fidelity[C]//Proceeding of 1995 Internation Conference of Image Processing.Washington:[s.N.],343-345
  • 4Watson A B,Solomon J A.Model of visual contrast gain control and pattern masking[J].Journal of Optical Society of America,1997,14(9):2379-2391
  • 5Vanden C J,Branden Lambrecht,Costantini D M,et al,Quality assessment of motion rendition in video coding[J].IEEE Trans Circuits and Systems for Video Tech,1999,9(5):766-782
  • 6Zhou Wang,Liang Lu,Alan C Bovik.Video quality assessment using structural distortion measurement[C]// Proceeding of 2002 Intemation Conference of Image Processing.Rochester,New York:[s.N.],Ⅲ-65-68
  • 7RRNR-TV group test plan.Draft version 1.7[EB/OL].2004[2005 -01-10].http://www.vqeg.org
  • 8Wang Zhou,Alan C Bovik,Eero P.Simoncelli.Handbook of image and video processing[M].2 nd ed,New York:Academic Press,2005
  • 9Vladimir N Vapnik.An overview of statistical learning theory[J].IEEE Transactions on Neural Networks,1999,10 (5):988-999
  • 10JPEG-release1 _database[DB/OL].2005.Http://live.Ece.utexas.Edu/index.Htm

共引文献29

同被引文献20

引证文献4

二级引证文献10

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部