Optical character recognition system using multiple images and method of use

摘要

Disclosed is an improved OCR system wherein the same can be utilized for capturing and analyzing multiple images of a document to increase the efficiency and accuracy of digitizing printed texts on the document. Captured images are merged into a single set of character recognition results via a recognition method from multiple images, which include early fusion, late fusion, and hybrid fusion embodiments. The end product from each of the embodiments provides text and metadata that include recognized words. In late and hybrid fusion, words having confidence scores above a predetermined threshold are assembled together to form paragraphs to reconstruct a digital version of the document. In this way, the present invention utilizes multiple images that can be combined to aggregate information and achieve high accuracy when scanning and digitizing printed texts.

主权项

1. An optical text recognition method, comprising the steps of:
acquiring, with a camera, at least one set of multiple images of a document having texts thereon by adjusting scanning motion based on real-time feedback images of captured images, wherein said at least one set of multiple images comprise said captured images; determining whether two or more of said at least one set of multiple images of said document overlap, wherein each of said at least one set of multiple images comprise different parts of said document; combining said at least one set of multiple images via image fusion to form at least one merged image; processing each of said at least one merged image through single frame document recognition to produce at least one set of text and metadata of said at least one merged image.