Image Denoising Based on Combined Neural Networks Filter

Author

Junhong Chen ; Qinyu Zhang

Author_Institution

Shenzhen Grad. Sch., Dept. of Electron. & Inf. Eng., Harbin Inst. of Technol., Shenzhen, China

fYear

2009

fDate

19-20 Dec. 2009

Firstpage

1

Lastpage

4

Abstract

In this paper, a new image restoration method based on combined neural networks Alter is proposed. This combined neural networks Alter is posed by a BPNN Alter and an image data fusion system based on self-organizing mapping neural networks. And this approach can use the corrupted image itself as training data to avoid the problem of how to choose the training data, which is most of the other neural networks denoising methods have to face, by using the distributed character of WGN. Experiment results show that the proposed method can denoise the noises effectively.

Keywords

filtering theory; image denoising; image restoration; self-organising feature maps; sensor fusion; Alter; image data fusion system; image denoising; image restoration; neural networks filter; self-organizing mapping neural networks; Digital filters; Digital images; Image denoising; Image restoration; Information filtering; Information filters; Neural networks; Noise reduction; Training data; White noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Engineering and Computer Science, 2009. ICIECS 2009. International Conference on

Conference_Location

Wuhan

Print_ISBN

978-1-4244-4994-1

Type

conf

DOI

10.1109/ICIECS.2009.5363487

Filename

5363487