APPLICATION OF GENETIC ALGORITHM ON CERTAIN PROBLEMS OF PATTERN RECOGNITION

Abstract

The present thesis aims to realize problems of Pattern Recognition using Genetic Algorithm to derive the benefits of genetic algorithm in the area of optimization procedure, for structural pattern recognition. Among the various transform frameworks in which pattern recognition has been traditionally formulated, the structural approach is considered to be the most intensively studied approach, when morphology (topology) of the pattern, is going to be the main classifier of the patterns. The pattern analyzed for this study is in the form a character pattern. As the characters can be well represented in the form of their shape numbers, which is based on the morphology of the character, the structural recognition approach is followed to efficiently recognize the characters. The issues carefully taken care by the recognition system are: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection. In order to achieve the desired objective, ...