Recognition of pattern defects of printed circuit board using topological information

The authors discuss an optical inspection system in which topological information on conductors and insulators of PCBs (printed circuit boards) is used for the detection of defects. The conventional image comparison methods, such as direct comparison of two images and image expansion-contraction for a design-rule inspection, have some difficulties in finding large defects, missing patterns, and a short. To cope with these problems, topological information on PCBs is introduced in this proposed method. This will also make it easy to access computer-aided design data for the inspection process. The principle of the system is mainly based on the topological comparison method which compares the inspection graph obtained from the skeletons of the conductor and insulator images of an inspection PCB with those of the standard or reference board. Topological information incorporates weighted graphs composed of several types of nodes and edges, connections, and their locations. Both conductor and insulator graphs have such information