Devnagari Handwritten Numeral Recognition using Geometric Features and Statistical Combination Classifier
This work addresses digit recognition for Devanagari script users, but it is incremental as it applies existing statistical methods to a specific dataset without major innovations.
The paper tackled handwritten Devanagari numeral recognition by using 17 geometric features and multiple discriminant functions, achieving improved accuracy through a majority voting combination classifier that outperformed individual classifiers on a dataset of 1500 training and 1500 testing samples.
This paper presents a Devnagari Numerical recognition method based on statistical discriminant functions. 17 geometric features based on pixel connectivity, lines, line directions, holes, image area, perimeter, eccentricity, solidity, orientation etc. are used for representing the numerals. Five discriminant functions viz. Linear, Quadratic, Diaglinear, Diagquadratic and Mahalanobis distance are used for classification. 1500 handwritten numerals are used for training. Another 1500 handwritten numerals are used for testing. Experimental results show that Linear, Quadratic and Mahalanobis discriminant functions provide better results. Results of these three Discriminants are fed to a majority voting type Combination classifier. It is found that Combination classifier offers better results over individual classifiers.