Printing defect detection method based on flexible template registration

Abstract

A printing defect detection method based on a flexible template registration comprising the following steps: adopting a rigid registration for initial positioning; using a training sample subjected to rigid initial registration as well as overall similarity measure and coordinate difference degree of all pixels of a standard image as an optimization goal to acquire a flexible registration image from the standard image to the training sample; obtaining a high-value image and a low-value image by studying a training sample set subjected to flexible registration; and finally determining whether the grayscale and / or the color of all images to be detected exceed(s) the value range of high and low template or not so as to obtain a defect image. The method can ensure the image detection accuracy while maintaining tolerance on destabilizing factors such as deformation, so that not only can be the misinformation probability of machine vision inspection reduced, but also the risk of leakage waste can be reduced, which is greatly conducive to improving the detection accuracy.

Description

technical field [0001] The invention relates to a printing defect detection method with low probability of false alarm and low risk of waste leakage, which belongs to the technical field of printing. Background technique [0002] Existing printing defect detection systems mainly use rigid template registration technology. This type of traditional method performs multi-level image search and positioning on the current image to be inspected, selects a specific image block as a search and positioning template image, and performs search and positioning through translation to determine the defect location. The advantages of this type of method are simple data processing and calculation, fast detection speed, and good detection sensitivity when the image is stable. However, potential unstable factors in the process of manufacturing and inspection of printed matter are unavoidable, and these factors will lead to free geometric deformation of the image. Instability factors mainly ...

AI Technical Summary

Problems solved by technology

In most cases, these inconsistencies in printed matter are within the allowable range of product quality, that is, they do not constitute defects

However, because the traditional template registration technology uses a rigid registration mode, the tolerance for geometric inconsistency of the image is weak, so a large number of false positives will inevitably be generated during the detection process, resulting in a huge waste of products and human resources, and resulting in low productivity

Images