Express waybill information identification method and system based on deep learning

Abstract

The invention discloses an express waybill information identification method and system based on deep learning. The method comprises the following steps: constructing a convolutional neural network, and training the convolutional neural network according to all types of sample express waybill images on the market to obtain an image classification model; acquiring image information of an express to be sent, performing image processing for the image information, and acquiring information of a target express waybill, wherein the information of the target express waybill at least includes regional information and contour information; performing comparative calculation according to the contour information and preset side length information, and zooming the regional information based on a comparative calculation result to obtain a thumbnail image; and inputting the thumbnail image to the image classification model, and performing identification to obtain bar code information and destination information in the thumbnail image. According to the express waybill information identification method and system disclosed by the invention, the efficiency of image identification can be improved, the accuracy of image identification can also be greatly increased, and particularly, the accuracy of identifying destinations in express waybills can be greatly increased.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a deep learning-based express delivery order information recognition method and system. Background technique [0002] With the advent of the new technological revolution and the information age, the development of e-commerce has become increasingly mature, making online shopping gradually become people's favorite shopping method or even the main shopping method; The large increase has made the speed of sorting more and more demanding. The current sorting speed has been improved from the traditional method of manually scanning the express delivery list with a scanning gun to an automatic one by setting up a camera and image analysis. The method of scanning and obtaining barcodes and destinations uses traditional digital image and pattern recognition methods to analyze and process images. Although the image recognition function is realized, the image recognition e...

AI Technical Summary

Problems solved by technology

[0002] With the advent of the new technological revolution and the information age, the development of e-commerce has become increasingly mature, making online shopping gradually become people's favorite shopping method or even the main shopping method; The large increase has made the speed of sorting more and more demanding. The current sorting speed has been improved from the traditional method of manually scanning the express delivery list with a scanning gun to an automatic one by setting up a camera and image analysis. The method of scanning and obtaining barcodes and destinations uses traditional digital image and pattern recognition methods to analyze and process images. Although the image recognition function is realized, the image recognition efficiency is low and the error rate is high, which seriously affects the sorting speed. and efficiency

Images