The defect detection of personalized print based on template matching

Abstract

Personalized printings are more and more used widely in daily life because it is better suited to people's aesthetics. Compared with conventional prints, its surface is more complicated and irregular, so the conventional algorithm of template matching cannot accurately detect its defects. Aimed at this case, a kind of algorithm named secondary template matching is proposed in this paper, Firstly, the image to be tested and the template image is matched to extract ROI, and then the four-threshold algorithm is used to distinguish the foreground and the background of the image. Finally, the second template matching for the foreground and background areas is performed to extract the defect respectively. From the experimental results, it can be found that the new algorithm of template matching can accurately detect the defects of the printed matter and the robustness.