The Community for Technology Leaders
Green Image
<p>The task of automating the visual inspection of pin-in-hole solder joints is addressed. Two approaches are explored: statistical pattern recognition and expert systems. An objective dimensionality-reduction method is used to enhance the performance of traditional statistical pattern recognition approaches by decorrelating feature data, generating feature weights, and reducing run-time computations. The expert system uses features in a manner more analogous to the visual clues that a human inspector would rely on for classification. Rules using these cues are developed, and a voting scheme is implemented to accumulate classification evidence incrementally. Both methods compared favorably with human inspector performance.</p>
computer vision; automatic joint inspection; PCBs; decorrelation; pin-in-hole solder joints; statistical pattern recognition; expert systems; objective dimensionality-reduction method; feature data; feature weights; voting scheme; classification evidence; computer vision; computerised pattern recognition; electronic engineering computing; expert systems; inspection; printed circuit testing
P.J. Besl, D. Mukherjee, C.L. Cole, K.D. Skifstad, R. Jain, S.L. Bartlett, "Automatic Solder Joint Inspection", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 10, no. , pp. 31-43, January 1988, doi:10.1109/34.3865
48 ms
(Ver 3.3 (11022016))