Journal Article

Enhanced CNN for image denoising

Wang, Junqian, Luo, Nan, Xu, Yong, Fei, Lunke, Wen, Jie, Tian, Chunwei

2019

Overview

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.

• Publisher: The Institution of Engineering and Technology,John Wiley & Sons, Inc,Wiley
• Subject: Artificial neural networks / authors / B6135 Optical, image and video signal processing / batch normalisation techniques / C5260B Computer vision and image processing techniques / C5290 Neural computing techniques / convolution / convolutional neural denoising network / deep convolutional neural networks / deep network architecture / Deeper networks / dilated convolutions / enhanced CNN / flexible architectures / image denoising / Image enhancement / image representation / image restoration / image restoration CNN / learning (artificial intelligence) / neural nets / Noise / Noise reduction / performance saturation / Research Article / residual learning / training difficulties