A method for determining address format in the automated sorting of Japanese mail

This paper presents a new method for determining the address format used on mail that has been hand-written in Japanese, a task made particularly difficult by the variety of formats possible in Japanese. We classify possible formats into six types, and identify the distinguishing features of each. In the proposed method, features characterizing any of the six types are identified for a given address, and from this a list of format-candidates is generated. Character lines are then determined for any format candidate, and one candidate is subsequently selected on the basis of the statistical likelihood of any address being written in that particular way, given the location and size of the character lines. We also demonstrate the effectiveness of the new method experimentally.