A Statistical Approach for Handwritten Character Recognition Using Bayesian Filter

This paper proposes a new handwritten character recognition method using a statistical technique based on Bayes' theorem. This technique is the so-called Bayesian filter. The Bayesian filter was originally intended for spam mail recognition, and is known to be a very effective approach. Consequently, we applied the Bayesian filter method to recognition of handwritten characters read by a scanner. Experimental results indicated that the proposed method has high recognition performance in spite its simplicity.