The number of parameters introduced for typological surface specification is ever increasing. Methods are thus required for assessing the weight of the different parameters with respect to classification problems. In order to provide a flexible tool for comparing surfaces and the relative influence of the variables, an approach based on pattern recognition and classification techniques is presented. The use of such techniques for analysis and clustering of machined surfaces is discussed, by adopting the MST algorithm. An application to simulated profiles is also presented. © 1985 CIRP.
Pattern Recognition Approach to Surface Classification
LONARDO, PIETRO;BRUZZONE, ALESSANDRO;
1985-01-01
Abstract
The number of parameters introduced for typological surface specification is ever increasing. Methods are thus required for assessing the weight of the different parameters with respect to classification problems. In order to provide a flexible tool for comparing surfaces and the relative influence of the variables, an approach based on pattern recognition and classification techniques is presented. The use of such techniques for analysis and clustering of machined surfaces is discussed, by adopting the MST algorithm. An application to simulated profiles is also presented. © 1985 CIRP.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
