Printing Defects Detection Based on Two-Times Difference Image Method

Abstract

With an aim at printing quality on-line detection, a method based on two-times difference image algorithm was proposed. Firstly, a standard template image and a gray threshold value image were calculated by using statistical methods. Secondly, an abnormal spots image was obtained through two-times difference image of the detection image, the standard template image and gray threshold value image. Lastly, the defects can be detected by analysis of connected region of the abnormal spots image. The results demonstrated that the problems of false detection and omission detection due to edge of image can be solved effectively, and the detection accuracy can be improved through this method.

Industrial Printing Image Defect Detection Using Multi-Edge Feature Fusion Algorithm

“…e abovementioned detection methods all applied image difference to extract defective patterns. Because the defective image and standard image collected in reality often have interferences with size, rotation, deformation, and other factors, whether the two images can be well registered will directly affect the accuracy of defect detection [16]. Image registration needs to be considered from the feature space, search space, interpolation method, search strategy, similarity measurement, and other aspects [6].…”

Real-time Defect Detection Method for Printed Images Based on Grayscale and Gradient Differences

“…Traditional printing defects are detected manually. However, the artificial detection is difficult to meet the requirement of batch production of packaging products because of high cost, slow speed and low recognition rate.. With the development of intelligent and informational technology, machine vision has been widely used in industrial inspection [1][2][3][4][5]. Compared with the traditional manual detection method, automatic detection based on machine vision can reduce the labor intensity of inspectors and improve detection efficiency and accuracy [6][7] with the feature of non-contact, fast speed, and anti-interference.…”

“…However, since the reference image and the inspected image are not acquired at the same time, and the production environment may be greatly changed, the relative coordinates of the camera and the subject are not the same world coordinates during the process of capturing image. Although some of the above problems can be solved by image pre-processing, image correction, image registration, and so on, the artifact contours and defects brought by the simple image difference method become indistinguishable, which reduces the accuracy of defect detection [22,23].To cope with the artifacts caused by image difference, various false-contour removal methods have been developed based on mathematical morphology (MM) [24,25],shading template [5,26], and neighborhood iterative difference [22]. In the MM-based method, the size of the structural element must be greater than those of false contours and false defects.…”