Address-block extraction by Bayesian rule

Abstract

A method for extracting a recipient address-block from a mail image has been developed. The method is composed of two steps: nomination of address-block candidates and evaluation of these candidates by using the Bayesian rule according to each of address-block type. Accordingly, the proposed method can cope with various types of address-blocks. The effectiveness of the method was confirmed in several address extraction experiments. These experiments show that the top-five extraction results include one correct address-block in 94% of total number of printed-mail cases and 89% in of handwritten-mail cases.