Printed Character Recognition based on Shape Descriptors with Competitive Neural Trees

Abstract

Competitive Neural Trees (CNeT) are widely used for classification in pattern recognition. This paper applies this technique for recognizing of Myanmar printed character s . This paper involves three important steps, typically preprocessing, feature extraction and classification. The aim of prepro cessing is to improve the quality of the images for further processing . After pre processing, features for each character image are extracted based on Shape description. Shape is an important visual feature and it is one of the basic features used to descr ibe image content. These feature vector from word images which are used in Competitive Neural Trees (CNeT) for recognition purpose. This paper introduces a global search method for the CNeT, which is utilized for training.