Handwritten Numeral Recognition Based on Reduced Features Extraction and Fuzzy Membership Functions

Abstract

We design and develop a handwritten numeral recognition system based on reduced features extraction and fuzzy membership functions with the intention to find a minimal set of feature primitives without sacrificing the recognition rate. We first perform preprocessing of smoothing and thinning to obtain a skeleton for each image. We then extract the following feature primitives for each skeleton: loop, horizontal, vertical, C-like curve, and D-like curve. Two fuzzy S-functions are used as membership functions to estimate their likelihood of being close to the top and to the bottom. A tree-like classifier based on the reduced feature primitives and fuzzy memberships is then applied to recognize the numerals.