DOCUMENT PROCESSING APPARATUS, METHOD AND PROGRAM

摘要

PROBLEM TO BE SOLVED: To provide a document processing apparatus, method and program which can generate a document file capable of relieving the load of a document processing. SOLUTION: The document processing apparatus includes: a partial image extract section 20 that extracts one or more partial images included in either of text document areas and non-text areas from the document file wherein the text document areas and the non-text areas are mixed; a layout information generating section 40 for generating layout information of the partial images extracted by the partial image extract section 20; a functionalized processing section 30 for applying functional approximation processing to the partial images extracted by the partial image extract section 20 to extract a feature quantity; and a document file storage section 50 for storing the feature quantity extracted by the functionalized processing section 30 on the basis of the layout information produced by the layout information generating section 40. COPYRIGHT: (C)2007,JPO&INPIT