METHOD AND SYSTEM FOR ANALYZING LAYOUT OF DOCUMENT

摘要

PROBLEM TO BE SOLVED: To provide a new format applicable to a document provided with a determined layout such as a from or the like by comparing adjacency relation between cells in the document with the adjacency relation between the cells stipulated by format data and specifying the corresponding cell stipulated by the format data in the document. SOLUTION: A format recording part 11 stores the information of a format based on the adjacency relation of the cells and a format generation part 12 generates the format from the sample of the and confirms the continuity of the cell. A reader 13 generates the image data of the form and stores them in a storage part 14 and a cell extraction part 15 extracts the cell from the image data and obtains the adjacency relation between the cells of the slip. A layout analysis part 16 performs matching with the adjacency relation stipulated by the format between the cells of the form and specifies which cell of the format the cell in the slip corresponds to by comparing them.