Title :
Syntactic pattern recognition by quadratic neural nets. A case study: rail flaw classification
Author :
McKenzie, Patricia ; Alder, Mike
Author_Institution :
Centre for Intelligent Inf. Process. Syst., Western Australia Univ., Nedlands, WA, Australia
Abstract :
We show how quadratic neural nets can be used to accomplish syntactic pattern recognition. The method has been applied successfully to an industrial problem of classifying rail flaws by examining ultrasonic images.
Keywords :
civil engineering computing; engineering; flaw detection; image classification; neural nets; railways; ultrasonic imaging; ultrasonic materials testing; industrial problem; quadratic neural nets; rail flaw classification; syntactic pattern recognition; ultrasonic images; Computer aided software engineering; Covariance matrix; Fasteners; Information processing; Intelligent systems; Mathematics; Neural networks; Pattern recognition; Rails; Statistical analysis;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.714138
