Title :
Automatic inspection of assembled PC board via highlight separation and dual channel processing
Author :
Park, Jong-Seok ; Tou, Julius T.
Author_Institution :
Central Res. Lab., Gold Star Co. Ltd., Seoul, South Korea
Abstract :
The design of an automated inspection system for electronic components on a printed circuit board is presented. The inspection system employs several unique methodologies. They are (1) a normal vector equalization method for separating probable highlights and obtaining two forms of image information, i.e. Lambertian images and specular images, (2) a dual-channel processing strategy for maximizing the utilization of the information concealed in those two types of images, and (3) a proximity-measure-based decision-making algorithm for detecting defective components. The system has been tested for several PC boards and experimental results have shown promise
Keywords :
automatic optical inspection; computer vision; decision theory; printed circuit testing; Lambertian images; PC testing; assembled PC board; automated inspection system; automatic optical inspection; computer vision; defective components detection; dual channel processing; electronic components; highlight separation; normal vector equalization method; proximity-measure-based decision-making algorithm; specular images; Assembly; Electronic components; Electronic equipment testing; Electronics industry; Infrared detectors; Inspection; Optical reflection; Printed circuits; Soldering; Surface-mount technology;
Conference_Titel :
Robotics and Automation, 1991. Proceedings., 1991 IEEE International Conference on
Conference_Location :
Sacramento, CA
Print_ISBN :
0-8186-2163-X
DOI :
10.1109/ROBOT.1991.132039
