A SUBPATTERN LEVEL INSPECTION SYSTEM FOR PRINTED-CIRCUIT BOARDS

The existing inspection systems are algorithmically slow and suffer fr om many drawbacks in meeting the inspection requirements of printed ci rcuit board fabrication. The system presented in this paper can handle all of the defects simultaneously with the same approach and is signi ficantly faster compared to the existing approaches. The system consis ts of three major phases: the first step is the segmentation of the go lden PCB image into basic subpatterns, the second step is the learning phase, and the third and final step is the verification/inspection ph ase. The system presented here introduces the application of neural ne tworks and fuzzy logic in printed circuit board inspection. The method is highly parallel and works at the subpattern level. Experimental re sults which demonstrate the effectiveness of the proposed algorithms a re given, (C) 1998 Academic Press.