Share Email Print
cover

Proceedings Paper

Image denoising algorithm based on adversarial learning using joint loss function
Author(s): Yongyi Yu; Meng Chang; Huajun Feng; Zhihai Xu; Qi Li; Yueting Chen
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A generative adversarial network denoising algorithm which uses a combination of three kinds of loss functions was proposed to avoid the loss of image details in the denoising process. The mean square error loss function was used to make the denoising results similar to the original images, the perceptual loss function was used to understand the image semantic information, and the adversarial learning loss function was used to make images more realistic. The algorithm used the deep residual network, the densely connected convolutional network and a wide and shallow network as the component in the replaceable module of the network. The results show that the three networks tested can make images more detailed and have better peak signal to noise ratio while removing image noise. Among them, the wide and shallow network which uses fewer layers, larger convolution kernels and more feature maps achieves the best result.

Paper Details

Date Published: 7 November 2018
PDF: 7 pages
Proc. SPIE 10832, Fifth Conference on Frontiers in Optical Imaging Technology and Applications, 108320U (7 November 2018); doi: 10.1117/12.2507518
Show Author Affiliations
Yongyi Yu, Zhejiang Univ. (China)
Meng Chang, Zhejiang Univ. (China)
Huajun Feng, Zhejiang Univ. (China)
Zhihai Xu, Zhejiang Univ. (China)
Qi Li, Zhejiang Univ. (China)
Yueting Chen, Zhejiang Univ. (China)


Published in SPIE Proceedings Vol. 10832:
Fifth Conference on Frontiers in Optical Imaging Technology and Applications
Junhao Chu; Wenqing Liu; Huilin Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top