Method and device for detecting tiny bearing surface defect by computer vision technology

Abstract

The invention relates to a computer visual detecting field and provides a method and a device for detecting defects on the surfaces of a tiny bearing by adopting computer visual technology. The technical proposal is that: the system for detecting the defects on the surface of the tiny bearing works on line in a production line; arranging the tiny bearing (4) needed to be detected on an automatic line (5) and leading a digital camera to shoot the surface image of the bearing through the control of a sensor when the tiny bearing moves to the lower side of the digital camera; a cold light source (2) changes the beams into parallel beams through a telecentric lens (3) to lead the beams to vertically illume the surface of the bearing; using a dark box (6) to insulate the bearing from the outside optical source; transmitting collected gray images to the computer through an image collecting card and analyzing automatically whether the bearing has defects by using special software according to the gray changes of the images; a removing mechanism automatically removes the bearings with defects. The device can be conveniently connected with a bearing production line, has a simple structure, is easy to be maintained and has low device investment.

Description

technical field [0001] The invention relates to the field of computer vision detection, in particular to a method for detecting defects on the surface of tiny bearings through computer vision technology and a device invented for realizing the method. Background technique [0002] In recent years, with the improvement of technical level, the requirements for product surface quality have also been greatly improved. Due to the large output of tiny bearings, the size, depth and distribution of pits and scratches on the surface are random. Enterprises usually use manual visual inspection to complete this work, which not only requires a large amount of labor, but also has low efficiency and a high rate of missed inspections, which affects the quality of products leaving the factory. Users often return and exchange things, which not only cause economic losses, but also bring users Negative impact. The use of computer vision detection technology for non-contact detection is the bes...

AI Technical Summary

Problems solved by technology

[0009] The problem to be solved by the present invention is to overcome the problems of low efficiency and poor reliability caused by manual detection of bearing defects

Images