Classification of Kannada Numerals Using Multi-layer Neural Network

Abstract

A simple multilayer feed forward neural network based classification of handwritten as well as printed Kannada numerals is presented in this paper. A feed forward neural network is an artificial neural network where connections between the units do not form a directed cycle. Here four sets of Kannada numerals from 0 to 9 are used for training the network and one set is tested using the proposed algorithm. The input scanned document image containing Kannada numerals is binarized and a negative transformation is applied followed by noise elimination. Edge detection is carried out and then dilation is applied using 3 × 3 structuring element. The holes present in this image are filled. Every image is then segmented out forming 50 segmented images each containing one numeral, which is then resized. A multilayer feed forward neural network is created and this network is trained with 40 neural images. Then testing has been performed over ten numeral images. The proposed algorithm could perfectly able to classify and recognize the printed numerals with different fonts and hand written numerals.