An OCR System for Printed Kannada Text Using Two - Stage Multi-network Classification Approach Employing Wavelet Features

Neural network based approaches have been steadily gaining performance and popularity for wide range of optical character recognition (OCR) applications. Conventional neural networks are not suitable for classification problems involving large-set of patterns because of large computational time requirement and difficulty in determining network structure. In this paper we present an OCR system for recognition of complete set of printed Kannada characters, which are more than 600 in number. Two-stage multi-network neural classifiers are used to cope with the large-set character classification problem. Wavelets that have been progressively used in pattern recognition are used in our system to extract the features. An encouraging recognition rate of about 91% is got at character level.