Machine vision-based stainless steel soup ladle defect detection method

Abstract

The invention provides a machine vision-based stainless steel soup ladle defect detection method. The machine vision-based stainless steel soup ladle defect detection method comprises the following steps: S1), acquiring a to-be-detected stainless steel soup ladle surface defect image; S2), sequentially performing graying, gray scale transformation and image smoothing pretreatment on the acquired surface defect image; S3), performing threshold segmentation on the pretreated image by an automatic threshold segmentation method to obtain a plurality of independent areas; S4), eliminating misjudgedpixel points and tolerable tiny defects through area characteristics and judging whether defects exist in the products or not; and S5), classifying the products with the defects through roundness characteristics and performing pixel area calculation and positioning on the defects in the image. By the method, the defect detection of the stainless steel soup ladle can be realized, the detection accurate rate of the stainless steel soup ladle product surface scratch defects is up to 100 percent, the integrated defect detection accurate rate is up to 96 percent or more, different types of defectsof the soup ladle can be detected pertinently, the detection efficiency is high, and the detection stability is achieved.

Description

technical field [0001] The invention relates to the technical field of spoon defect detection, in particular to a machine vision-based defect detection method for stainless steel spoons. Background technique [0002] Due to the problems of high reflection and easy imaging of stainless steel products, it is difficult for machines to identify and classify the surface details. At present, stainless steel tableware manufacturers mainly rely on manual inspection of stainless steel products, and human eyes cannot distinguish between qualified and No, this will cause the problem of low defect detection accuracy and high false detection rate. [0003] With the rapid development of science and technology, computer vision detection technology has emerged. At present, the main method of visual detection of surface defects is to realize the automatic detection of surface defects of metal parts through genetic algorithm and visual image processing form, such as a kind of workpiece appea...

AI Technical Summary

Problems solved by technology

However, when these two methods deal with images with more textures, image information will be lost, and when dealing with Gaussian noise effects and rough surfaces, the effect is not obvious.

Images