Enhanced CNN for image denoising  

作　　者：Chunwei Tian Yong Xu Lunke Fei Junqian Wang Jie Wen Nan Luo 

机构地区：[1]Bio-Computing Research Center,Harbin Institute of Technology,Shenzhen,Shenzhen 518055,People’s Republic of China [2]Shenzhen Medical Biometrics Perception and Analysis Engineering Laboratory,Harbin Institute of Technology,Shenzhen,Shenzhen 518055,People’s Republic of China [3]School of Computer Science and Technology,Guangdong University of Technology,Guangzhou 510006,People’s Republic of China [4]Institute of Automation Heilongjiang Academy of Sciences,Harbin 150090,People’s Republic of China

出　　处：《CAAI Transactions on Intelligence Technology》2019年第1期17-23,共7页智能技术学报（英文）

摘　　要：Owing to the flexible architectures of deep convolutional neural networks(CNNs)are successfully used for image denoising.However,they suffer from the following drawbacks:(i)deep network architecture is very difficult to train.(ii)Deeper networks face the challenge of performance saturation.In this study,the authors propose a novel method called enhanced convolutional neural denoising network(ECNDNet).Specifically,they use residual learning and batch normalisation techniques to address the problem of training difficulties and accelerate the convergence of the network.In addition,dilated convolutions are used in the proposed network to enlarge the context information and reduce the computational cost.Extensive experiments demonstrate that the ECNDNet outperforms the state-of-the-art methods for image denoising.

关 键 词：ECNDNet CNNS 

分 类 号：G[文化科学]