Using moments features from Gabor directional images for Kannada handwriting character recognition

Abstract

Handwriting character recognition (HCR) for Indian Languages is an important problem where there is relatively little work has been done. In this paper, we investigate the moments features on Kannada handwritten basic character set of 49 letters. Moments features are extracted from the preprocessed original images by most of the researchers. Kannada characters are curved in nature with some symmetry observed in the shape. This information can be best extracted as a feature if we extract moment features from the directional images. So we are finding 4 directional images using Gabor wavelets from the dynamically preprocessed original images. We then extract moments features from them. The comparison of moments features of 4 directional images with original images when tested on Multi Layer Perceptron with Back Propagation Neural Network shows an average improvement of 13% from 72% to 85%. The mean performance of the system with these two features together is 92%.

DOI: 10.1145/1741906.1741916

Extracted Key Phrases

8 Figures and Tables

Cite this paper

@inproceedings{Ragha2010UsingMF, title={Using moments features from Gabor directional images for Kannada handwriting character recognition}, author={L. R. Ragha and M. Sasikumar}, booktitle={ICWET}, year={2010} }