Detection of defects in automotive metal components through computer vision

Abstract

This article introduces the progresses made on the development of an automatic visual inspection for automotive metal components. These components may present three types of defects, which are: central hole closed or partially closed; absence of thread on the bolts; burr on the weld connections. For each type of defect different image processing and analysis algorithms were tested and a specific setup (type and pose of the cameras and illumination) was developed. The results suggest a good efficiency of the vision system and its potential full spreading industrialization.