Method, electronic device, and storage medium for intelligently detecting defective glass images

Abstract

This application is about a method for intelligently detecting defective glass images. The method includes: acquiring a photographed image of the glass to be tested; performing image preprocessing on the photographed image to obtain a preprocessed image; performing image segmentation processing on the preprocessed image to obtain a first glass image; if the first glass image has an image If there is a defect, the closing operation is performed on the first glass image to obtain a second glass image; the second glass image is subtracted from the first glass image to obtain a defective glass image representing the shape of the defect. The solution provided by this application avoids the error caused by manual measurement by automatically detecting the edge image of cut glass, and can improve the product detection efficiency of the glass production line, thereby reducing the risk of defective glass products entering the market due to uneven cutting. improve product quality.

Description

technical field [0001] The present application relates to the technical field of defective glass image detection, and in particular, to a method for automatically detecting defective glass images, an electronic device, and a storage medium. Background technique [0002] Glass has been around for thousands of years and is one of the most versatile man-made materials in high-tech fields. In the screen display industry, liquid crystal glass is a high-tech optoelectronic glass product formed by encapsulating liquid crystals in glass by means of high temperature and high pressure. Today, liquid crystal glass is widely used as a dimming device for electronic equipment, and the upper and lower polarizers are attached to the color film through the boxing process, and the bottom plus the backlight can form a liquid crystal display (Liquid Crystal Display, LCD for short). An important component of the current display device. [0003] In the thin film transistor liquid crystal displa...

AI Technical Summary

Problems solved by technology

[0003] In the Thin film transistor liquid crystal display (TFT-LCD) industry, because the production of large-size glass substrates can effectively improve the yield and output rate of large-screen LCD panels, while reducing production costs, so in In the production process, the glass substrate is always enlarged, and then cut according to the actual production needs. The four sides of the cut glass are required to be straight lines, which is an important control parameter in the glass production process; Fine cutting knife wheel and movement, the straightness of edge cutting will fluctuate, and there will be local protrusions or depressions on the edge, resulting in fragments, under-grinding, burning edges, cracks, etc., which seriously affect product quality

[0004] At present, the measurement method of defective glass is often measured by personnel operating a vernier caliper or a two-dimensional image measuring instrument, and adjusted according to the four-sided linearity measurement data. The application of these two methods makes the entire adjustment process more cumbersome, longer detection time, and poor operability. , the measurement data is inaccurate, and it is inconvenient to save defect data, which is not conducive to data backtracking

Images