English Character Recognition using Quadrant Feature Extraction Method and Artificial Neural Nework

Abstract

This paper proposes a scheme for recognition of English characters based on features derived from partitioning the character image into quadrant cells. Pixel counted from each quadrant in anticlockwise direction; contribute towards generation of the feature vector. A total of 51 quadrants lead to the generation of a 51-element feature vector. A neural network (multi-layered perception) is used for classifying the 26 alphabets of the English language. Accuracies obtained are demonstrated to have been improved upon with respect to contemporary works. Keywords: quadrant feature; neural network; multilayered perception; feature vector