NeuroFuzzy Network Schemes for Impulsive Noise Reduction in Digital Images

Abstract

Noise reduction or noise removal is an important task in image processing. In general, Results of the noise removal have a strong influence on the quality of the following image processing techniques. On the other side, the integrated system of neurofuzzy networks are more interesting and applied for different applications. In this contribution, two neurofuzzy network schemes have been presented for impulsive noise removal. The computation is reduced by using an artificial image in training. High performances are obtained. Results of neurofuzzy schemes show that the performance is increased as the ratio of the noise is increased. The presented schemes are used for grayscale and also for true color images.