Fuzzy Model Based Recognition of Handwritten Hindi Numerals using Bacterial Foraging

This paper presents the recognition of handwritten Hindi numerals. The recognition is based on the modified exponential membership function fitted to the fuzzy sets derived from features consisting of normalized distances obtained using the Box approach. The exponential membership function is modified by two structural parameters that are estimated by optimizing the entropy subject to the attainment of membership function to unity. The optimization strategy used is the foraging model of E.coli bacteria. Two window sizes are used: one for ( ) and another for the rest of the numerals. Experimentation is carried out on a limited database of nearly 3500 samples. The overall recognition is found to be 96%.