Method for machine vision detection in allusion to self-focusing lens surface defect

Abstract

The invention discloses a method for machine vision detection in allusion to a self-focusing lens surface defect. The method comprises the following steps: 1, controlling open and close of 1+n groups of light sources, to obtain 1+n original images of two end faces of a self-focusing lens; 2, using the first image, executing the circular target area image location and 8-degree slope and right-angle surface judgment, using dynamic threshold segmentation to obtain a binary image, extracting the suspected defect area feature, and giving out the product qualified or unqualified judgment; 3, if the judgment is a qualified product, dividing the target image on n rest images according to the circular target area position, executing median filtering differential treatment to the target mage, and executing pit detection, executing the scratch detection on the divided target image by using the shape feature of the tiny scratch, and giving out a detection result; and 4, executing the defect detection to 1+n images of two end faces, and executing the comprehensive judgment to the product. The method is capable of solving the problem in the prior art that the artificial detection efficiency is low and the detection quality is unstable.

Description

technical field [0001] The invention belongs to the technical field of detection methods for surface defects of industrial products, and relates to a method for machine vision detection for surface defects of self-focusing lenses. Background technique [0002] Self-focusing lens is a kind of tiny optical device widely used in optical fiber communication, micro optical system, medical optical instrument and other equipment, and its surface quality has a great influence on the performance of the product. Its surface quality defects are mainly chipping, pitting and scratches, and the probability of scratches is higher. The prior art is to observe the position, size and type of defects manually under a microscope, and subjectively determine the classification level of the defects. This method has the following disadvantages: the detection efficiency is low, the work intensity is high, the product quality is greatly affected by human factors, the inspection quality varies from p...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for machine vision detection of surface defects of self-focusing lenses, which solves the problems of low manual detection efficiency and unstable detection quality in the prior art

Images