Printed circuit board inspection using image analysis

Computer vision has been widely used in the online inspection of electronic components. In this paper, the authors present a computer vision system using structured lighting, which provides them with an efficient solution for solder joint inspection. Their system uses a novel structured-lighting inspection technology to overcome some difficulties that traditional computer vision systems often experience. They developed a slant map surface shape estimation technique for the solder joint. From this technique, a solder joint can be determined to be a good (concave), bad (convex), bridged solder joint, or solder joint with surplus solder, or lacking solder.

[1]  David W. Capson,et al.  A Tiered-Color Illumination Approach for Machine Inspection of Solder Joints , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Horng-Hai Loh,et al.  Printed circuit board inspection using image analysis , 1995, Proceedings IEEE Conference on Industrial Automation and Control Emerging Technology Applications.

[3]  Lee E. Weiss,et al.  Structured Highlight Inspection of Specular Surfaces , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Yasuo Nakagawa Automatic Visual Inspection Of Solder Joints On Printed Circuit Boards , 1982, Other Conferences.

[5]  Shigeki Kobayashi,et al.  Identifying solder surface orientation from color highlight images , 1990, [Proceedings] IECON '90: 16th Annual Conference of IEEE Industrial Electronics Society.