Mechanical visual identification of batch parts based on Halcon software

Abstract

∗In recent years, with the vigorous development of information technology, the already verymature industry has been further developed, a large number of factories from the original production mode gradually upgraded to semi-automation, and constantly close to full automation. In the research and development process of production automation, machine vision technology, as a very key technology, has gradually become a hot research field. With the advantages of high detection accuracy, high efficiency, and non-contact, it has been widely used in the appearance and defect detection of mechanical parts. Quality inspection of parts is an important link that must be carried out before the use of parts. Only qualified parts can meet the requirements of use. Traditional detection methods cannot meet the requirements of detection due to high cost and low precision. In this article, through further study of machine vision detection technology, build the test platform based on machine vision technology, from hardware selection, the visual system design, research, and camera calibration algorithm, etc, on this basis, the mechanical parts of parallelism and perpendicularity, alignment, and parts of shape defect detection as the research target, select the appropriate object detection, all of them have reached the actual requirement of detection.