Document image Chinese keyword detection method and system based on single word matching

Abstract

The invention belongs to the technical field of text image recognition. The invention relates to a detection method and system, in particular to a document image Chinese keyword detection method and system based on single word matching. In order to solve the problems of low accuracy and robustness of Chinese keyword recognition caused by unstable quality of a document image and diversity of Chinese character arrangement, the method comprises the following steps: carrying out binarization processing on the document image to obtain a first image; performing character detection to obtain a firstcandidate character set; filtering the first candidate character set to obtain a second candidate character set and a first noise candidate character set; screening characters from the first noise candidate character set and adding the characters to a second candidate character set to obtain a third candidate character set; performing candidate character combination to obtain a first candidate word set; carrying out secondary detection on the lost characters to obtain a second candidate word set; and selecting a final keyword detection result based on the cost function. According to the method, the accuracy of document keyword recognition is improved, and the robustness is high.

Description

technical field [0001] The invention belongs to the technical field of text image recognition, and in particular relates to a method and a system for detecting Chinese keywords in document images based on word matching. Background technique [0002] The development of science and technology has made the way of information processing advance by leaps and bounds. In order to realize the processing of information editing, searching and data analysis, it is of great significance to quickly input the text information of paper materials into the computer, and OCR (Optical Character Recognition) technology was born from this. Document images widely exist in various fields such as transportation, finance, logistics, taxation, and administrative management. With the rapid popularization of smart terminals, automatic document recognition technology has great economic benefits and extensive social value. [0003] However, it is difficult for general OCR technology to provide structured...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem of insufficient accuracy and robustness of Chinese keyword recognition caused by the instability of document image image quality and the diversity of Chinese character arrangements, the first aspect of the present invention proposes A method for detecting Chinese keywords in document images based on word matching is proposed, the method includes the following steps:

Images