Document extracting method and document extracting apparatus
AssigneeSharp Kabushiki Kaisha
InventorHitoshi Hirohata
Life of this patent
Estimating the term…
Abstract
Document data corresponding to each page included in a document is stored, and furthermore, feature data indicative of a feature of the document data and a document index indicating the document are associated with the document data. A document extracting apparatus obtains input document data, calculates feature data from the input document data, judges similarity between the input document data and the document data based on the feature data, obtains a document index associated with document data similar to the input document data, and extracts a plurality of pieces of document data associated with the document index. Thus, document data concerning the document including a page corresponding to the document data similar to the input document data is extracted for a plurality of pages.
Claims9
A document extracting method for extracting specific document data from stored document data, the method comprising steps of:
- storing a document index in association with document data corresponding to each page included in the document;
- the document index including a page index having page indices respectively indicating pages of the document data and a number of pages for each document;
- 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;
- obtaining input document data serving as new document data;
- extracting a feature point from the obtained input document data;
- generating feature data indicative of a feature of the input document data based on the extracted feature point;
- comparing the generated feature data with the stored feature data, thereby judging similarity between the document data associated with the stored feature data, and the input document data;
- obtaining a document index associated with document data judged as document data highly similar to the input document data;
- and
- extracting a plurality of pieces of document data corresponding to a plurality of pages included in a document indicated by the obtained document index.
A document extracting apparatus comprising:
- a processing device;
- a storage device storing instructions that, when executed by the processing device, cause the processing device to implement:
- storing a document index, the document index including a page index having page indices respectively indicating pages of the document data and a number of pages for each document in association with document data corresponding to each page included in the document;
- storing feature data, calculated based on a feature point extracted from the document data and indicative of a feature of the document data, in association with the document data;
- obtaining input document data serving as new document data;
- extracting a feature point from the input document data;
- generating feature data indicative of a feature of the input document data based on the extracted feature point;
- comparing the generated feature data with the stored feature data, thereby judging similarity between the document data associated with the feature data and the input document data;
- obtaining a document index associated with document data that is judged as document data highly similar to the input document data;
- and
- extracting a plurality of pieces of document data corresponding to a plurality of pages included in a document indicated by the obtained document index.
A non-transitory 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 the document index including a page index having page indices respectively indicating pages of the document data and a number of pages for each document;
- 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.
Dependencies are inferred from the claim text.