Combined Classifiers in Recognition of Handwritten Kannada Numerals: a Hybrid Approach

The recognition of handwritten numeral is an important area of research for its applications in post office, banks and other organizations. This paper presents automatic recognition of handwritten Kannada numerals using both unsupervised and supervised classifiers. Four different types of structural features, namely, direction frequency code, water reservoir, end points and average boundary length from the minimal bounding box are used in the recognition of numeral. The effect of each feature and their combination in the numeral classification is analyzed. Combining classifiers has proved to be an effective solution to several classification problems in pattern recognition. In the image classification, it is often beneficial to consider each feature type separately, and to integrate the initial classification results by a final classifier. In this paper, we developed a robust hybrid approach where fuzzy k-Nearest Neighbor (fuzzy k-NN) and fuzzy c-means (FCM) as base classifiers for individual feature sets, the results of which together forms the feature vector for the final k-Nearest Neighbor (k-NN) classifier. Testing is done, using different feature sets, individually and in combination, on a database containing 1600 samples of different numerals and the results are compared with the different existing methods.