Proceedings of the 14th International conference on Industrial and engineering applications of artificial intelligence and expert systems: engineering of intelligent systems
Exhaustive Detection of Manufacturing Flaws as Abnormalities
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
The feature extraction and analysis of flaw detection and classification in BGA gold-plating areas
Expert Systems with Applications: An International Journal
Hi-index | 0.15 |
Research was performed on the detection of faults such as shorts, cuts, and nicks in a printed circuit board pattern. The possibility was investigated of detecting a pattern by illuminating a printed circuit board with violet or ultraviolet rays and detecting the pattern using the (yellow or other) fluorescent light emitted by the base material consisting of glass-epoxy or glass-polyimide, etc. It was found that the pattern could be detected clearly by selecting an optical fiber that would separate the emitted fluorescent light from the illumination and using a detector consisting of a high-sensitivity TV camera that produces a silhouette image in which the base material is bright and the pattern is dark. A printed-circuit-board pattern inspector using this approach was developed. Test operation of the inspector in a plant demonstrated that it performs consistently good pattern inspections.