Image denoising method based on a deep convolution neural network. Issue 4 (1st April 2018)

• Record Type: Journal Article
• Authors: Zhang, Fu; Cai, Nian; Wu, Jixiu; Cen, Guandong; Wang, Han; Chen, Xindu
• Is Part Of: IET image processing. Volume 12:Issue 4(2018)
• Page Start: 485
• Page End: 493
• Publication Date: 2018-04-01
• Subjects: image denoising -- feedforward neural nets -- gradient methods -- convergence of numerical methods; image denoising method -- deep convolution neural network -- DCNN -- contaminated image -- latent clear image -- training stage -- gradient clipping scheme -- noise levels -- single denoising model; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2017.0389
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Image denoising is still a challenging problem in image processing. The authors propose a novel image denoising method based on a deep convolution neural network (DCNN). Different from other learning‐based methods, the authors design a DCNN to achieve the noise image. Thus, the latent clear image can be achieved by separating the noise image from the contaminated image. At the training stage, the gradient clipping scheme is employed to prevent gradient explosions and enables the network to converge quickly. Experimental results demonstrate that the proposed denoising method can achieve a better performance compared with the state‐of‐the‐art denoising methods. Also, the results indicate that the denoising method has the ability of suppressing different noises with different noise levels by means of one single denoising model.