Invoice information extraction method combined with two-dimensional code recognition

Abstract

The invention belongs to the technical field of invoice information extraction, and particularly relates to an invoice information extraction method combining two-dimensional code recognition, which comprises the following steps: S1, carrying out bill text recognition; s2, carrying out bill two-dimensional code identification; and S3, selecting an identification result: after output information ofbill text identification and bill two-dimensional code identification is obtained, analyzing and accepting or rejecting the two groups of information, deriving an approximate position of a two-dimensional code according to a text identification result, and performing positioning identification on the two-dimensional code by using a deep learning technology. The two-dimensional code identificationrate is far higher than that of a traditional method. According to the method, text recognition and two-dimensional code recognition results are accepted or rejected according to the confidence coefficient, the recognition accuracy is further guaranteed, meanwhile, the text and the two-dimensional code are recognized, and when information of one party is defective, the result of the other party can supplement the final result advantageously. The method can adapt to more complex and changeable scenes, and has higher robustness.

Description

technical field [0001] The invention relates to the technical field of invoice information extraction, in particular to an invoice information extraction method combined with two-dimensional code identification. Background technique [0002] The information contained in the invoice image is very rich. In addition to the text information printed on the invoice, the QR code on the upper left corner of the invoice also encodes the main information of the invoice (such as invoice number, invoice code, amount, invoice date, etc.), how to effectively Extracting this information is the key to invoice identification technology. [0003] One of the existing methods is to only locate and analyze the QR code of the invoice, because the QR code already contains enough important information, as long as it is successfully decoded, the basic invoice information identification can be completed, but in actual application scenarios Invoices are often wrinkled and covered. Once the two-dimens...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for extracting invoice information combined with two-dimensional code identification, so as to solve the problem that the existing invoice information extraction proposed in the above-mentioned background technology mainly adopts a single identification text or two-dimensional code is easy to appear: two-dimensional code area If there is a defect or other conditions that make it impossible to locate and identify, all the information of the invoice cannot be obtained. In the case of a complex and changeable environment, it is difficult to achieve a high recognition accuracy of the QR code. Therefore, the overall recognition accuracy of the invoice little improvement

Images