An automatic detection method for printed matter defects based on machine vision

Abstract

The invention discloses a method for automatically detecting the defects of printed matters based on machine vision. The method comprises the following steps of firstly, adopting a convex shape matching method to carry out registration on the images of collected and qualified printed matters; then, forming an average image, a bright template image and a dark template image by means of the images of the qualified printed matters subjected to registration; finally, adopting the convex shape matching method to carry out registration on the image of a printed matter to be detected and the average image, marking the pixels, which are higher than the bright template image or lower than the dark template image, in the image to be detected as defect points, removing the isolated defect points and fusing discrete defect areas. According to the method for automatically detecting the defects of the printed matters based on machine vision, the convex shape matching method has the advantages of being rapid in image matching speed and high in matching precision; the designed defect detection method based on the bright template image and the dark template image is high in adaptability and can effectively detect the defects in the printed matters; the method provided by the invention can improve the accuracy and efficiency of a whole detection system.

Description

technical field [0001] The invention belongs to the technical field of printing, and in particular relates to a machine vision-based automatic detection method for printed matter defects. Background technique [0002] With the rapid development of modern printing presses, the printing speed is getting faster and faster, once a printing defect occurs, it will cause a lot of waste. On the other hand, high-speed printing makes it impossible to rely on manual monitoring of print quality. Therefore, printing companies urgently need an efficient and fully automatic print quality inspection system based on machine vision. [0003] In the defect detection method of printed matter based on machine vision, it involves the construction of standard templates, image matching and defect judgment. Since there is always a certain difference between qualified images in printing, the standard template constructed in the existing method is not flexible enough, and it is easy to cause false d...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for automatic detection of printed product defects based on machine vision, which solves the problems of slow matching of printed images and inaccurate detection in the prior art

Images