PROCESSING OF NOISY AND SMALL-DETAILED GRAY-SCALE IMAGES USING CELLULAR NEURAL NETWORKS

Algorithms oi filtering, edge detection, and extraction of details and their implementation using cellular neural networks (CNN) are develop ed in this paper The theory of CNN based on universal binary neurons ( UBN) is also developed. A new learning algorithm for this type of neur ons is carried out Implementation oi law-pass filtering algorithms usi ng CNN is considered. Separate processing of the binary planes of gray -scale images is proposed. Algorithms of edge detection and impulsive noise filtering based on this approach and their implementation using CNN-UBN are presented, Algorithms oi frequency correction reduced to f iltering in the spatial domain are considered. These algorithms make i t possible to extract details of given sizes. Implementation of such a lgorithms using CNN is presented. Finally, a general strategy of gray- scale image processing using CNN is considered. (C) 1997 SPIE and IS&T .