TY - JOUR
T1 - A two-stage-classifier for defect classification in optical media inspection
AU - Toth, Daniel
AU - Condurache, Alexandru
AU - Aach, Til
PY - 2002/12/1
Y1 - 2002/12/1
N2 - A pattern recognition system used for industrial inspection has to be highly reliable and fast. The reliability is essential for reducing the cost caused by incorrect decisions, while speed is necessary for real-time operation. In this paper we address the problem of inspecting optical media like Compact Disks and Digital Versatile Disks. Here, defective disks have to be identified during production. For optimizing the production process and in order to be able to decide how critical a certain defect is, the defects found have to be classified. As this has to be done on-line, the classification algorithm has to work very fast. Concerning speed, the well known minimum distance classifier is usually a good choice. However, when training data are not well clustered in feature-space this classifier becomes rather unreliable. To trade-off speed and reliability we propose a two-stagealgorithm. It combines fast minimum distance classification with a reliable fuzzy k-nearest neighbor classifier. The resulting two-stage-classifier is considerably faster than the fuzzy k-nearest neighbor classifier. Its classification rates are in the range of the fuzzy k-nearest neighbor classifier and far better than those of the minimum distance classifier. To evaluate the results, we compare them to the results obtained using various standard classifiers.
AB - A pattern recognition system used for industrial inspection has to be highly reliable and fast. The reliability is essential for reducing the cost caused by incorrect decisions, while speed is necessary for real-time operation. In this paper we address the problem of inspecting optical media like Compact Disks and Digital Versatile Disks. Here, defective disks have to be identified during production. For optimizing the production process and in order to be able to decide how critical a certain defect is, the defects found have to be classified. As this has to be done on-line, the classification algorithm has to work very fast. Concerning speed, the well known minimum distance classifier is usually a good choice. However, when training data are not well clustered in feature-space this classifier becomes rather unreliable. To trade-off speed and reliability we propose a two-stagealgorithm. It combines fast minimum distance classification with a reliable fuzzy k-nearest neighbor classifier. The resulting two-stage-classifier is considerably faster than the fuzzy k-nearest neighbor classifier. Its classification rates are in the range of the fuzzy k-nearest neighbor classifier and far better than those of the minimum distance classifier. To evaluate the results, we compare them to the results obtained using various standard classifiers.
UR - http://www.scopus.com/inward/record.url?scp=33845233642&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2002.1047473
DO - 10.1109/ICPR.2002.1047473
M3 - Journal articles
AN - SCOPUS:33845233642
SN - 1051-4651
VL - 16
SP - 373
EP - 376
JO - Proceedings - International Conference on Pattern Recognition
JF - Proceedings - International Conference on Pattern Recognition
IS - 4
ER -