NON-LINEAR STATISTICAL TECHNIQUES FOR IMAGE RESTORATION

Abstract

Digital signal processing is concerned with the representation of signals by sequence of numbers or symbols and the processing of such sequences. The basic purpose of collecting data for sequences is to extract meaningful information about the phenomenon of interest. Often, the phenomenon is not physically observable and the information about it is obtainable only through some measuring instrument or system. The data available may be a linear superposition of the desired quantities. This type of linear information mixing is peculiar to a large number of diversified fields in physical sciences. The main problem confronted in these fields is how to unmix the data. When the phenomenon of interest, is an image then the processing of the data is termed as digital image processing.