Document extracting method and document extracting apparatus

A document extracting apparatus, including a document storage section for storing document data, for extracting specific document data from the document data stored in the document storage section, the apparatus comprising:

• a document index storage section for storing a document index, indicating a document including a plurality of pages, in association with document data corresponding to each page included in the document;
• a feature data storage section for storing feature data, calculated based on a feature point extracted from document data and indicative of a feature of the document data, in association with the document data;
• a document data obtaining section for obtaining input document data serving as new document data;
• a feature point extracting section for extracting a feature point from the input document data obtained by the document data obtaining section;
• a generation section for generating feature data indicative of a feature of the input document data based on the feature point extracted by the feature point extracting section;
• a judgment section for comparing the feature data, generated by the generation section, with the feature data stored in the feature data storage section, thereby judging similarity between the document data associated with the feature data stored in the feature data storage section, and the input document data;
• a document index obtaining section for obtaining a document index associated with document data that is judged as document data highly similar to the input document data by the judgment section;
• and
• a document data extracting section for extracting a plurality of pieces of document data corresponding to a plurality of pages included in a document indicated by the document index obtained by the document index obtaining section.

A computer-readable memory product which stores a computer program for causing a computer to extract specific document data from document data stored inside or outside the computer,

• wherein the computer program comprises steps of:
• causing the computer to extract a feature point from input document data that has been inputted;
• causing the computer to generate feature data indicative of a feature of the input document data based on the extracted feature point;
• causing the computer to compare the generated feature data with feature data indicative of a feature of the stored document data, thereby judging similarity between the stored document data and the input document data;
• causing the computer to obtain a document index associated with document data judged as document data highly similar to the input document data;
• and
• causing the computer to extract a plurality of pieces of document data corresponding to a plurality of pages included in a document indicated by the obtained document index.