2002 Volume 122 Issue 8 Pages 1301-1308
In signal processing applications and image processing applications, some problems are difficult to process based on the linear theory. In these problems, nonlinear processing will be more suitable for obtaining better results. On the other hand, neural networks with a nonlinear input-output relation are applied to various problems such as pattern recognition and the estimation of nonlinear systems. This paper presents a method for noise removal for degraded images using neural networks. Furthermore, in order to effectively apply neural networks to noise removal of the images with different features from the teacher images, a method is proposed for using multiple neural networks to extract the features of the images properly. Finally, the results of computer simulation are presented to illustrate the effectiveness of the proposed method.
The transactions of the Institute of Electrical Engineers of Japan.C
The Journal of the Institute of Electrical Engineers of Japan