Product surface defect detection method

Abstract

The invention discloses a product surface defect detection method. The method employs a passive detection mode, which means that the method does not give consideration to the defects of the surface of a product or the defects and the characteristics of the defects, removes a no-defect region in a process of image processing, and leaves a defect part image. The method comprises the steps: firstly carrying out the threshold segmentation through an OTSU algorithm, and carrying out the image binaryzation of a gray scale map of an original image; secondly setting a defect threshold window epsilon and carrying out the secondary segmentation of an obtained binary image so as to remove the defects and background noises; finally proposing a local inhibition solution in order to solve a problem of edge burr of the image of the product, thereby obtaining an accurate and clear real defect image. The proposed passive detection mode can reduce the operation burden of an algorithm and increase the processing speed of the algorithm, and also can remove a pseudo-defect part formed by the edge burr caused by the illumination unevenness, and achieve the quick and accurate detection of the surface defects of the product.

Description

technical field [0001] The invention belongs to the technical field of product quality detection, and in particular relates to a method for detecting product surface defects. Background technique [0002] With the development of production and technology, people have paid more attention to the appearance quality of products, mainly including: ①Products whose value depends on product appearance quality, such as printing, packaging, handicrafts, etc.; ②Surface defects directly affect The use of the product or the deep processing of the product will bring great losses to the user or the deep processing customer. For example, in the process of optical cable manufacturing, the surface defects of the optical cable due to improper materials or processes not only reduce the physical strength of the optical cable, but also may cause damage to the cable. Cause damage inside the cable, which will change the optical performance of the cable, such as the dispersion loss of the optical fi...

AI Technical Summary

Problems solved by technology

[0004] Traditional manual detection has great limitations in actual use

First of all, manual inspection relies on people's subjective evaluation, and is affected by subjective and objective factors such as people's mood, thinking, and lighting. Many unstable and unreliable factors

Secondly, human eyes cannot realize online defect detection during high-speed production of products, and cannot meet the requirements for online real-time monitoring of the whole process of production quality

Images