Title :
Classifying cereal grains using backpropagation and cascade correlation networks
Author :
Dolenko, Brion ; Card, Howard ; Neuman, Michael ; Shwedyk, Edward
Author_Institution :
Institute for Biodiagnostics, National Research Council of Canada, 435 Ellice Ave., Winnipeg, Man. R3B 1Y6; Department of Electrical and Computer Engineering, University of Manitoba, Winnipeg, Man. R3T 5V6
fDate :
4/1/1995 12:00:00 AM
Abstract :
This paper presents backpropagation- and cascade correlation-trained artificial neural networks for cereal grain classification. In comparison with a Gaussian classification technique, the neural networks deliver higher classification accuracy and are more attractive for implementation in automated grain inspection systems.
Keywords :
Accuracy; Correlation; Image color analysis; Kernel; Logistics; Neurons; Training;
Journal_Title :
Electrical and Computer Engineering, Canadian Journal of
DOI :
10.1109/CJECE.1995.7102030
