Neural Network Based Offline Tamil Handwritten Character Recognition System

Authors:
J. Sutha;N. Ramaraj
Affiliations:
-;-
Venue:
ICCIMA '07 Proceedings of the International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007) - Volume 02
Year:
2007

Citing 0
Cited 3

Neural network based handwritten hindi character recognition system

Proceedings of the 2nd Bangalore Annual Compute Conference
Handwriting Recognition in Indian Regional Scripts: A Survey of Offline Techniques

ACM Transactions on Asian Language Information Processing (TALIP)
A data acquisition and analysis system for palm leaf documents in Telugu

Proceeding of the workshop on Document Analysis and Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we propose an approach to recognize handwritten Tamil characters using a multilayer perceptron with one hidden layer. The feature extracted from the handwritten character is Fourier Descriptors. Also an analysis was carried out to determine the number of hidden layer nodes to achieve high performance of backpropagation network in the recognition of handwritten Tamil characters. The system was trained using several different forms of handwriting provided by both male and female participants of different age groups. Test results indicate that Fourier Descriptors combined with backpropagation network provide good recognition accuracy of 97% for handwritten Tamil characters. Keywords : Indian Language, Feature Extraction, Handwritten character Recognition, Backpropagation network, Fourier Descriptors.