Document image analysis and recognition method and system

Abstract

The invention discloses a document image analysis and recognition system. The system comprises a user operation end, an interaction center, a process control end, a machine engine management end, a manual annotation management end, a machine terminal cluster and a manual terminal cluster, wherein the user operation end, the process control end, the machine engine management end and the manual annotation management end are respectively connected to the interaction center; the machine engine management end is connected with the machine terminal cluster; and the manual annotation management end is connected with the manual terminal cluster. In addition, the invention further discloses a document image analysis and recognition method. The document image analysis and recognition system has boththe efficiency of a machine and the accuracy of manual work, simple operation steps and reliable processing results are provided for users, meanwhile, a man-machine coupling mode can play a teachingrole on the machine in the continuous iteration process, and therefore, the performance of the machine is gradually enhanced, and the participation degree of the manual work is reduced.

Description

technical field [0001] The invention relates to the technical field of document image analysis and recognition, in particular to a document image analysis and recognition method and system. Background technique [0002] Optical Character Recognition (OCR) is an image file that converts the text in a paper document into a pixel matrix by optical means, and converts the text in the image into a text format through recognition software for text The technology of processing software for further editing and processing. [0003] Document Image Analysis and Recognition (DIAR for short) is a method that uses computer vision to analyze the physical and logical structure of document images, locate and identify various elements inside documents (such as text, tables, images, graphics, etc.) etc.), thereby forming a complete description of the document technology. [0004] A distributed software system is a software system that supports distributed processing, and is a system that exe...

AI Technical Summary

Problems solved by technology

[0012] However, the inventors have found through research that the document image analysis and recognition system in the prior art mainly has the following problems: 1. Incomplete functions, it can only provide some functions in the document image analysis and recognition, recognize several types of objects, and cannot form A complete description of the hierarchical structure of document images; 2. The accuracy is not high, and high recognition accuracy cannot be guaranteed for document images with poor quality and complex layouts; 3. Lack of comprehensive manual proofreading tools and services, users use poor experience

[0013] In addition, due to cost or efficiency reasons, the existing technical solution cannot provide a complete processing flow, and some processing steps are missing, so it is difficult to obtain a complete description of the document information; in addition, the existing technical solution only simply provides software tools and lacks follow-up Functions such as proofreading and verification need to be solved separately by the user, which increases the difficulty of use

Images