Method for classifying business card character clauses and device thereof

Abstract

The present invention relates to a method for classifying business card character clauses and a device thereof, belonging to the field of optical character recognition. The method comprises the following steps: (a) a complete match classifying step according to guide terms, in which complete match test is carried out for the character clauses with all guide terms in a complete match guide term table one by one, the character clauses passing the test of the step are sent to classified results, and the character clauses failing the test go to the next step; (b) a fault-tolerant match classifying step according to guide terms, in which the character clauses passing the test of the step are sent to classified results, and the character clauses failing the test go to the next step; (c) a fault-tolerant match classifying step according to keywords, in which the character clauses passing the test of the step are sent to classified results, and the character clauses failing the test go to the next step; (d) a classifying step according to the logic structure characteristics of page layouts. The business card character clauses of various page layout structures can be quickly and accurately classified by the present invention.

Description

technical field [0001] The present invention relates to optical character recognition (Optical Character Recognition, hereinafter referred to as: OCR), in particular to a method and device for classifying character entries of business cards. Background technique [0002] In today's business activities, business cards are already an important information carrier for business partners, customers, etc. Faced with a large number of business cards, companies and individuals need a way to automatically and accurately collect and process information. The current practice is generally It is to first obtain the image of the business card (such as input by mobile phone, digital camera, scanner, etc.), then analyze the layout physical structure of the business card image to locate the character area, and obtain the binary image of the character area through image processing, and then analyze the two The last and most important step is to understand the category attributes of the charac...

AI Technical Summary

Problems solved by technology

[0005] The disadvantage of the above technology is that the first two patent applications only use layout logic structure features, and several layout logic structure templates given in the paper are too restrictive to adapt to the changing layout structure of business cards; the third patent application is also the main Using layout logic structure features, semantic information is only used for address entries; the fourth patent application uses semantic information and layout logic structure information comprehensively, but it sets priority for the use of semantic information, and does not consider the fault tolerance of semantic information Matching does not take into account the differences in the contribution of different keywords to classification performance, which have an important impact on classification performance

Images