An application of rough set theory to defect detection of automotive glass

A technique based on rough set theory is investigated for identifying defects on a backlight (a rear window of a vehicle with a defrost circuit). Since replacement of defective backlights result in a significant financial loss, automobile manufacturers are trying to remove defective backlights during the manufacturing process. Therefore, an automated inspection system based on infrared (IR) imaging techniques has been developed to detect backlight defects such as missing lines or hotspots, where the most challenging task is identifying hotspots from their artifacts.

[1]  Jaroslaw Stepaniuk,et al.  Rough Set Data Mining of Diabetes Data , 1999, ISMIS.

[2]  S. Tor,et al.  A Rough-Set-Based Approach for Classification and Rule Induction , 1999 .

[3]  Shusaku Tsumoto.  Automated Discovery of Plausible Rules Based on Rough Sets and Rough Inclusion , 1999, PAKDD.

[4]  Z. Pawlak.  Rough Sets: Theoretical Aspects of Reasoning about Data , 1991 .

[5]  Zdzislaw Pawlak,et al.  Data Mining - a Rough Set Perspective , 1999, PAKDD.

[6]  S. Fujimori,et al.  Analysis of discharge currents with discernibility matrices , 1998, Proceedings of 1998 International Symposium on Electrical Insulating Materials. 1998 Asian International Conference on Dielectrics and Electrical Insulation. 30th Symposium on Electrical Insulating Ma.