Title :
Invariant web defect detection and classification system
Author :
Rohrmus, Dominik
Author_Institution :
Siemens Corp. Res. Inc., Princeton, NJ, USA
Abstract :
We present a live web defect detection and classification system that runs on a Laptop PC with an attached camera. Features, invariant with respect to rotation and translation based on local integration are extracted from the grabbed images. They are then presented to a neural network for classification
Keywords :
automatic optical inspection; image classification; textile industry; Laptop PC; classification; neural network; rotation; translation; web defect detection; Cameras; Educational institutions; Feature extraction; Gray-scale; Inspection; Neurons; Petroleum; Pixel; Portable computers; Universal Serial Bus;
Conference_Titel :
Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on
Conference_Location :
Hilton Head Island, SC
Print_ISBN :
0-7695-0662-3
DOI :
10.1109/CVPR.2000.854963
