Printing film defect visual detection method and system

Abstract

The embodiment of the invention provides a printing film defect visual detection method and system. The method comprises the following steps: respectively shooting and imaging the left half part and the right half part of a printing film; extracting feature points of an overlapping area of the left image and the right image, searching for corresponding feature point pairs in the two images, calculating the difference of row coordinates of the feature point pairs, calculating the average value of the difference, taking the average value as a row deviation value of the left image and the right image, and aligning the two images in the row direction; selecting a defect-free image aligned by the method as a reference image, drawing a minimum rectangular region of interest including printed characters and pattern modes, and creating a Halcon-based shape template; and calculating the plate circumference length of the printing mode, and generating a reference template image of the printing mode. The to-be-detected image is detected by using the Halcon-based deviation model, so that defects in the to-be-detected printing film image can be accurately detected, defective products are rejected, the production process is improved, and the production quality of the printing film is greatly ensured.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a large-format printing film defect visual inspection method and system. Background technique [0002] Cross waterproof membrane is widely used in construction, outdoor advertising, logo and other industries in our country. And this kind of film is characterized by large format and good flexibility. [0003] Such large-format flexible films will have problems such as holes, wire drawing, creases, missing characters, ink dragging, crystal dots, and missing silicone oil during the printing production process, which will affect the quality of the finished product to a certain extent. [0004] For this type of film, most of the industry currently adopts manual off-line sampling inspection, which has low detection efficiency and lag, and requires operators to concentrate for a long time, which is prone to missing defects, resulting in batch defects and seriously affecting prod...

AI Technical Summary

Problems solved by technology

[0005] However, the general printing inspection technology based on machine vision is aimed at the inspection of small-format printed matter, and it is difficult to carry out effective defect detection for this large-format flexible printing film.

Images