Study on automatic surface check of gear parts

Abstract

This study treats the defect detection of the gear parts with image processing. The gear was put on the turn table and its side part was lightened by the LED light equipped on the USB camera. The obtained image was converted to the binalization one. Here, we focused on the fact that the reflection points appeared at the defects. As a result, we could find the optimal threshold value to detect the defects point. Moreover, it could be also confirmed that the reflected points could be appeared by setting the optimal threshold. The detected position of the reflected points may help us to find the edge line of the gear because the reflected points were always located at the extension of the edge line.