초록

An document image that is the source of Optical Character Recognition (OCR) output is displayed so that a user can select a region of the displayed document image. When the region is selected, text of the OCR output corresponding to the selected region is submitted as an input to a search engine.

대표청구항 ▼

[ I claim:] [1.]1. A computer readable media bearing sequences of computer executable instructions for retrieving documents from a database, comprising the computer-implemented steps of:creating a plurality of document images from a plurality of documents;recognizing characters in said document imag

[ I claim:] [1.]1. A computer readable media bearing sequences of computer executable instructions for retrieving documents from a database, comprising the computer-implemented steps of:creating a plurality of document images from a plurality of documents;recognizing characters in said document images to produce a document text;determining regions of the document images that correspond to words of the document text;correlating said regions with said text;searching said text in response to a query;retrieving document text in response to said search;displaying the corresponding document image;receiving an input that selects a portion of the document image;determining a selected text from the document text that corresponds to the portion of the document image;generating an updated query from said selected text; andsearching said text in response to said updated query.