METHOD FOR AUTOMATICALLY GENERATING DOCUMENT IDENTIFICATION DICTIONARY AND DOCUMENT PROCESSING SYSTEM

摘要

PROBLEM TO BE SOLVED: To automatically generate a knowledge dictionary recording a character string arrangement pattern to be used for document identification processing by using document image samples. SOLUTION: A character string extraction part 102 automatically extracts a character string from a document image by using a character string recognizing method in a document identification system. A stability calculation part 103 calculates the stability of each character string by checking the appearance frequency of the extracted character string. An inherency calculation part 104 calculates inherency by checking the number of document sorts in which each character string appears in character string data B to be an output from the calculation part 103. A character string priority calculation part 105 calculates registration priority on the basis of the value of inherency calculated by the calculation part 104 and other features of the character string. A document identification dictionary output part 106 generates a document identification dictionary in accordance with the registration priority of respective character strings.