Discrimination of fish species with neural networks: Reduction in number of inputs by an analysis of feature data
2005
Taira, Y.(National Fisheries Univ., Shimonoseki, Yamaguchi (Japan)) | Morimoto, E. | Nakamura, M.
We have developed a discrimination method of fish species by neural networks with image processing data. In this method, automatic procedure from fish image processing to fish species discrimination was achieved. Furthermore, the experiment in discrimination of fish species was successfully performed. The method, however, needs a large number of the feature parameters of a fish image used as the inputs of the neural network. Therefore, the method is unsuitable for implementation because this means that a tremendous amount of calculation is needed. In this report, we address the problem of reduction in the number of the feature parameters, i.e., the inputs of the neural network by means of an analysis of the feature data. The experimental results in this report showed that the number of inputs can be reduced from 19 to 4.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par Agriculture, Forestry and Fisheries Research Information Technology Center
Découvrez la collection de ce fournisseur de données dans AGRIS