Two-dimensional code positioning method based on translation invariance and small-area template matching

Abstract

The invention discloses a two-dimensional code positioning method and system based on translation invariance and small area template matching, and belongs to the related technical field of industrialtwo-dimensional code positioning, and the method comprises the following steps: collecting images of a product transmitted on a high-speed conveyor belt in real time, selecting a plurality of key areas with obvious features for each image in an image queue, carrying out template setting on the plurality of key areas by adopting a small area template matching algorithm, carrying out template matching processing in a fixed search area, combining the gradient amplitude with rotation invariance with a rapid search matching algorithm based on gradient amplitude characteristics, and positioning keyareas; achieving accurate positioning of the two-dimensional code according to the size of the two-dimensional code and the obtained center coordinate of the two-dimensional code, and then achieving two-dimensional code recognition; and when the recognized two-dimensional code is inconsistent with the original content of the two-dimensional code, determining that the recognized two-dimensional code is unqualified. The method meets the requirements of a high-speed production line for real-time detection and online real-time sorting of products printed with the two-dimensional code.

Description

technical field [0001] The invention relates to the related technical field of industrial two-dimensional code positioning, in particular to a two-dimensional code positioning method based on translation invariance and small-area template matching. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] In the industrial production industry, two-dimensional barcodes are a good medium for storing product information. The two-dimensional code has the characteristics of fast decoding speed, large amount of stored information and strong robustness, so it is of great significance for the classification and preservation of information data of products on the production line. However, in the process of industrial two-dimensional code printing, missing printing, wrong printing, and unclear printing occur from time to time. Once products with wrong mark...

AI Technical Summary

Problems solved by technology

[0004] At present, most industrial manufacturers use artificial vision for qualified detection of two-dimensional barcodes. Due to the poor visual consistency of human eyes and easy fatigue, the detection efficiency is low and the reliability is not high.

A small number of manufacturers use machine vision technology to detect product defects or printing defects. However, due to the poor collection environment on the industrial production line and the delay effect between the camera and the product, the collected QR code images will be distorted and blurred, etc. The problem is that in this case, even if the two-dimensional code is located, it cannot be decoded and recognized accurately. Therefore, a high-precision and high-efficiency two-dimensional barcode positioning and detection method and device are studied to meet the needs of industrial manufacturers. The requirement of high-speed and accurate detection is an urgent problem to be solved in this field

Images