A product defect-based optical detection method, system and readable storage medium

Abstract

The invention provides an optical detection method, system and readable storage medium based on product defects. The method includes: collecting the original image of the current product, and obtaining the grayscale image of the current product through binarization; Whether the number of grayscale images of historical products is greater than the first preset threshold N; if greater, select N grayscale images of historical products; compare the grayscale value of a pixel in the grayscale image of the current product with N The grayscale image of the historical product corresponds to the grayscale value of the pixel and calculates the difference one by one to obtain N difference values. If the absolute value of a certain difference value is greater than the second preset threshold, the pixel is marked as a defective reference point once. After comparing the absolute values ​​of the N differences, record the cumulative number of times the pixel is marked as a defect reference point; if the cumulative number is greater than the third preset threshold, mark the pixel in the grayscale image of the current product as a defect point. The invention improves detection efficiency and accuracy.

Description

technical field [0001] The invention relates to the technical field of optical detection, in particular to an optical detection method, system and readable storage medium based on product defects. Background technique [0002] With the continuous development of electronic devices such as displays and touch screens, the manufacturing of electronic devices is becoming more and more sophisticated. Due to the excessive and complicated process involved in the production of electronic devices, defects may occur in any link. Defect detection also puts forward higher requirements. [0003] The traditional method of detecting defects in electronic devices is mostly artificial visual inspection. For example, macroscopic defects are observed by naked eyes at various stages of electronic device production, but the detection accuracy is limited. At the same time, the artificial visual inspection method has subjective factors, great uncertainty, easy misjudgment and missed judgment, and ...

AI Technical Summary

Problems solved by technology

[0003] The traditional method of detecting electronic device defects is mostly artificial visual inspection. For example, in each stage of electronic device production, macroscopic defects are observed with the naked eye, but the detection accuracy is limited.

At the same time, the artificial visual inspection method has subjective factors, great uncertainty, easy misjudgment and missed judgment, and the accuracy of defect detection is not high

In addition, the manual visual inspection method has a low degree of automation, which further reduces the detection efficiency.

Images