Automated Optical Inspection System for O-Ring Based on Photometric Stereo and Machine Vision

This research developed an AOI (automated optical inspection) system for the O-Ring inspection. First, was implemented to detect surface scratches, flow marks, non-fills, and indentations on elastomer O-Rings with high reflection coefficients. The proposed employed multiple light source structures realize photometric stereo. method eased identification of contour Bézier control points. Then, by applying interpolation process these points, we estimated paths object surface. Simultaneously, regression analysis conducted produce a new smooth then constructed compared model built stereo method. difference deemed candidate defect location. Overall, detection recall rate 100% accuracy reached 96.56%. paper also dimension measurement. analyzed reversely calculated curve those points were used De Casteljau’s algorithm estimate accuracy.