High-precision receipt identification method and system based on OCR (Optical Character Recognition) technology

Abstract

The invention relates to a high-precision receipt recognition method and system based on an OCR technology, and the method comprises the steps: converting characters on a receipt into plane image information based on an optical scanning technology; scanning a character track on the front side of the document and the writing recess depth of the handwritten characters; based on the same principle, obtaining the handwriting protruding height of handwritten characters on the back of the document; for handwritten characters with unclear overlapped handwriting, listing characters possibly represented by the overlapped handwriting in sequence based on the depth of the handwriting concave trace and the height of the handwriting convex trace; obtaining character information from the plane image information, and inserting the character information into listed characters one by one to obtain a first character group sentence; and based on logic judgment, correct text sentences are selected to complete document recognition, and the method and the device can effectively improve the recognition precision of handwritten documents, especially for the scenes of wrong character altering, non-standard writing and the like.

Description

technical field [0001] The present application relates to the technical field of data sharing, in particular to a high-precision document recognition method and system based on OCR technology. Background technique [0002] OCR technology is the abbreviation of Optical Character Recognition (Optical Character Recognition). The computer input technique used. It can be applied to the input and processing fields of bank bills, a large amount of text materials, archives, and copywriting. It is suitable for automatic scanning identification and long-term storage of a large number of bill forms in banking, taxation and other industries. Compared with general texts, the final recognition rate, recognition speed, correct rate of layout understanding and satisfaction with layout restoration are usually used as the evaluation basis of OCR technology; compared with forms and bills, the recognition rate or the entire pass rate and recognition rate are usually used. Speed ​​is a practi...

AI Technical Summary

Problems solved by technology

[0003] The defect of the existing technology is: OCR technology is limited by the clarity and completeness of the document itself, and its recognition accuracy still has large errors compared with manual recognition, especially for handwritten documents, which have low intelligence and large errors Defects

Images