Sage Journals: Discover world-class research

Abstract

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 results 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 artefacts.

Feature selection techniques based on rough set theory are explored in this short communication and are used to extract a feature vector, which increases inspection accuracy as well as reduces computational complexity. The theory is also applied to generate decision rules, which can be simply added to existing inspection systems to assist the operators in their decision-making process. The proposed inspection system is expected to provide more reliable fault detection with low rate of false alarms than currently available systems.

Keywords

rough set theory automated inspection system feature selection rule generation automotive glass

References

Kim

Vachtsevanos

An automated IR-based inspection system for heated backlights. Technical Report, Georgia Institute of Technology, Intelligent Control Systems Laboratory, Atlanta, Georgia, February 2000.

Pawlak

Rough set elements. In Rough Sets in Knowledge Discovery 1: Methodology and Applications (Ed. Polkowski

Skowron

), 1998 (Physica-Verlag, Heidelberg).

Pawlak

Rough Sets: Theoretical Aspects of Reasoning about Data, 1991 (Kluwer, Deventer).

Pawlak

Data miningâa rough set perspective. In Proceedings of Third Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD′99), Beijing, PR China, April 1999, pp. 3–12.

Khoo

L. P.

Tor

S. B.

Zhai

L. Y.

A rough-set-based approach for classification and rule induction. Int. J. Advd Mfg Technologies, 1999, 15, 438–444.

Tsumoto

Automated discovery of plausible rules based on rough sets and rough inclusion. In Proceedings of Third Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD′99), Beijing, PR China, April 1999, pp. 210–219.

Stepaniuk

Rough set data mining of diabetes data. In Proceeding of the 11th International Symposium on Methodologies for Intelligent Systems (ISMIS′99), June 1999, pp. 457–465.

Fujimori

Kaiya

Inoue

Analysis of discharge currents with discernibility matrices. In Proceedings of the 1998 International Symposium on Electrical Insulating Materials, 1998, pp. 649–652.

Gonzalez

R. C.

Woods

R. E.

Digital Image Processing, 1993 (Addison-Wesley).

10.

Lee

Vachtsevanos

An application of rough set theory to defect detection of automotive glass. In Proceedings of the European Workshop on Information Forecasting, Diagnosis and Control (IFDICON′2001), Greece, 2001.