基于非对称卷积神经网络的图像去噪  

Image Denoising Based on Asymmetric Convolutional Neural Networks

作　　者：甘建旺 沙芸[1] 张国英[2] 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)

机构地区：[1]北京石油化工学院信息工程学院,北京102617 [2]中国矿业大学(北京)机电与信息工程学院,北京100083

出　　处：《激光与光电子学进展》2020年第22期193-198,共6页Laser & Optoelectronics Progress

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.

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 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]