Edge defect detection method and system for glass panel

Abstract

The invention is applicable to glass panel edge defect detection, and provides an edge defect detection method for a glass panel. The method comprises the steps of: A. performing glass panel image acquisition and performing gray-scale conversion, then performing binarization processing so as to obtain a binarization image, and extracting a contour of a region of interest; B. processing the contour of the region of interest so as to obtain a center line image, and traversing the center line image to obtain point coordinates of each point on a center line; C. extracting a gray-scale image corresponding to the contour of the region of interest, and obtaining a gray-scale value corresponding to the point according to the point coordinates; and D. processing the gray-scale value of the center line, then computing a gray-scale difference mean value of the center line, and determining whether an edge defect exists or not according to the gray-scale difference mean value of the center line and marking the edge defect. According to the edge defect detection method for the glass panel, which is provided by the present invention, the contour of the region of interest of the edge is extracted according to contour features of the edge of the glass panel, and defect detection is performed on the edge of the glass panel based on the gray-scale mean value of an adjacent region of the center line of the contour of the region of interest; and the method can be used for detecting defects of edges of multiple models of glass panels.

Description

technical field [0001] The invention belongs to the field of panel detection, and in particular relates to an edge defect detection method and system for a glass panel based on the average value of the centerline neighborhood gray scale. Background technique [0002] At present, there are three types of detection and identification methods for glass panel surface defects: image matching and comparison methods, non-image matching and comparison methods and hybrid methods. (1) Image matching and comparison method. This method is to match the standard image as a template with the detected image, that is, XOR operation. This method is suitable for defects such as gaps and edge bumps in the image, but for many types The edge defect of the glass panel is not fixed in length and width, so this method is not suitable for the edge defect detection of the glass panel of the mobile phone. (2) Non-image matching and comparison method This method does not require a template image, it ju...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a method and system for detecting edge defects of glass panels, aiming to solve the problems that the existing algorithms are complex, cannot meet the requirements of real-time detection, and the adaptability is not enough, and the system expansion ability is poor

Images