Traditional and neural networks algorithms: applications to the inspection of marble slab

This article describes the traditional algorithms of deterministic and stochastic cluster analysis and classification (a priori and with learning), by comparing the results obtained using the classifiers based on neural networking techniques in supervised learning (multilayer perceptron with backpro...

Full description

Saved in:
Bibliographic Details
Main Authors: Hernandez, V.G., Perez, P.C., Perez, L.G.G., Balibrea, L.M.T., Puyosa Pina, H.
Format: Conference Proceeding
Language:English
Subjects:
Backpropagation algorithms
Clustering algorithms
Color
Inspection
Neural networks
Robot vision systems
Service robots
Slabs
Statistics
Surface texture
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article describes the traditional algorithms of deterministic and stochastic cluster analysis and classification (a priori and with learning), by comparing the results obtained using the classifiers based on neural networking techniques in supervised learning (multilayer perceptron with backpropagation). The selected samples, chosen to check the algorithms have been marble slabs of "Sierra de la Puerta" type.
DOI:10.1109/ICSMC.1995.538408