Express sheet recognition method, system, terminal equipment and storage medium

Abstract

The invention discloses an express sheet recognition method, an express sheet recognition system, terminal equipment and a storage medium. The method comprises: obtaining an express sheet picture to be recognized by performing optical character recognition on the express sheet to be recognized; extracting features of the express sheet picture to be recognized by a full convolution network to obtain a target feature map; selecting a target positioning window from the preset candidate positioning window set by using a non-maximum value suppression algorithm; acquiring a current character image from the target feature map according to the target positioning window; substituting the current character image into the preset feature extraction model to obtain a character feature sequence, and inputting the character feature sequence to the cyclic neural network to obtain a character recognition result. The invention may accurately locate the text information in the express sheet to be recognized, and filter out the invalid information with low quality requirement for the express sheet picture as well as strong anti-interference ability, thereby reducing the workload of express sheet recognition, saving a large number of express sheet recognition time, improving the express sheet recognition speed, and improving the user experience.

Description

technical field [0001] The present invention relates to the field of optical identification, in particular to a method, system, terminal equipment and storage medium for identification of face sheets. Background technique [0002] In all walks of life, there are a large number of documents, such as bank notes, courier orders and so on. Using a purely manual input computer system requires a lot of manpower and time costs, and there are also disadvantages such as low timeliness and high error rate; compared with the traditional manual document input method, the recognition speed and accuracy of Optical Character Recognition (OCR) are lower. It has great advantages, which can save a lot of labor costs and improve the processing time of business. [0003] The existing OCR technology has disadvantages such as troublesome use, low anti-interference ability, high requirements on the image quality of documents, and the need to identify all text information on documents, which canno...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a bill recognition method, system, terminal equipment and storage medium, aiming to solve the troublesome use of pattern matching OCR technology in the prior art, low anti-interference ability, high requirements for the quality of bill pictures and inability to be accurate Technical issues in identifying documents

Images