A. Yajnik and S.R. Mohan (India)
Multi-Layer Perceptron, Daubechie’s wavelets, Neural Networks
This paper deals with the classification of a subset of printed Gujarati characters and modifiers. Very little work is found in the literature regarding the recognition of Gujarati script. In this paper two fairly representative sets of printed Gujarati characters and modifiers were chosen and subjected to classification by Artificial Neural Network architectures by considering linear activation functions in the output layer. The sample and test images for the Gujarati characters were obtained from the scanned images of printed Gujarati text and their features were extracted in terms of wavelet coefficients. Two Multi-Layer Perceptron (MLP) networks, one for the classification of alphabets which fall in the middle zone and the other one for classifying the modifiers which fall in the lower zone are designed. These networks achieve 94.46 % and 96.32 % of accuracy for alphabets and modifiers respectively on the test set. These recognition accuracies are higher than those quoted by any of the documented efforts so far for the Gujarati script.
Important Links:
Go Back
