Electronic official document recognition and reproduction method and system based on domestic CPU

Abstract

The invention discloses an electronic official document recognition and reproduction method and system based on a domestic CPU. The method comprises: S1, obtaining a picture format file of a paper official document; S2, extracting a text area in the picture, and preprocessing the text area; S3, performing element recognition on the processed content area, and further performing character recognition; S4, acquiring identification data, and analyzing the identification data; S5, displaying the identification data in an editable state in the form of an electronic official document; and S6, storing and storing the electronic official document. The system comprises a picture acquisition module, a picture preprocessing module, an official document identification module and a man-machine interaction module. Content identification is performed on the paper official document by referring to specifications of related official document formats, and the content of the paper official document is reproduced in an electronic official document manner, so that not only are storage and viewing in the future facilitated, but also the calculation complexity is reduced, and the processing efficiency and accuracy are improved.

Description

technical field [0001] The invention relates to OCR character recognition technology, in particular to a method and system for recognizing and reproducing electronic official documents based on a domestic CPU. Background technique [0002] Electronic official documents refer to digital official documents that are stored in digital form in disks, optical discs and other storage media, and rely on computer systems to read, process, and transmit digital official documents on communication networks. The system used to manage these electronic official documents is an electronic official document processing system. For the management of the life cycle of electronic documents and other processing matters. [0003] In the current e-government business scope, there are many ways to transmit official documents. Except in the form of public release, including newspaper broadcast, website publication or posting. The level-by-level, multi-level or leapfrog document delivery is limited ...

AI Technical Summary

Problems solved by technology

The improvement direction is mainly to improve the recognition rate, increase the compatible language and image format, etc., and there is no in-depth integration of electronic documents and electronic document processing systems through OCR text recognition technology.

Images