This paper presents Kannada handwritten numeral recognition system using fuzzy reasoning technique. The Kannada handwritten numeral database required for the experimentation is collected from the different individuals and preprocessed to obtain the binary images for feature extraction. The binary images are partitioned into a number of regions and extracted one feature from each by the zoning technique for their representation. The knowledge base is build using the statistical information involved in interclass region features. The features of unknown samples matched with the knowledge base and made the fuzzy reasoning for their classification. On experimentation with the training and testing samples, found better classification and recognition rate.

This paper presents the performance of Kannada handwritten numeral recognition using feed forward back propagation neural network (FFBPNN) classifiers. The classifier is designed to recognize the Kannada handwritten numerals. Samples are represented by the few features extracted by the zoning technique. The input numeral samples in binary form are stored in a fixed window size of 12x12 and partitioned into nine sub regions of 4x4 sizes for their representation. A normalized feature value is computed by the one"s present each sub region for their representation in two different approaches. On experimentation, it is found the overall recognition rate of 99.7% and 95.5% for the feature extraction approaches M 1 and M 2 respectively.