A Study of Indian Script Handwritten Characters Using Neural Networks

Exploring a novel MLP neural network approach for handwritten numeral recognition in Indian scripts

Abstract

In this paper hand-printed numeral identification, the numerals are supposed to be rendered legibly allowing for minor differences in the form of a numeral. Handwritten numeral identification is always the subject of research in the field of picture process and pattern recognition. Compared to the question of scanned numeral recognition, the issue of handwritten numeral recognition is exacerbated by differences in the shapes and sizes of handwritten English numerals. This makes the recognition of handwritten numerals or characters an intensive area of research in pattern recognition. Considering all these, the problem of handwritten numeral recognition is addressed under the present work in respect to handwritten English numerals. This dissertation presents a new approach for handwritten numeral recognition method using the MLP (Multi-Layer Perceptron) neural network for classification purpose.