Feature extraction based on stroke orientation estimation technique for handwritten numeral

The performance of any machine based recognition system heavily depends on the types of features used. More accurate the features extracted are, better is the chance of getting enhance performance in the recognition system. With this aim in mind a feature extraction method is proposed for numerals of Indian languages. It has been observed that structural feature are having an edge over the statistical feature used so far. Orientations of strokes that create a numeral play the most important role in the recognition. Orientations of pixels that create strokes are estimated from the image of the numerals and used as the main component of the proposed feature set. The efficiency of the feature set is then tested using a linear Support Vector Machine classifier. Results reported for large databases of Devanagari and Gujarati numerals are comparable with the highest recognition rate reported so far.