A multi-font character recognition based on its fundamental features by artificial neural networks

Abstract

Neural networks present an alternative approach for the character recognition problem. This paper describes the development of a recognition system of multi-font character using topological feature extraction to recognize capital isolated letters. By properly specifying a set of features such as vertical, horizontal, and slant strokes, curvature, open and closed areas, called here "fundamental features", the recognition was performed using a backpropagation neural network.