DIKUL - logo
Narodna in univerzitetna knjižnica, Ljubljana (NUK)
Naročanje gradiva za izposojo na dom
Naročanje gradiva za izposojo v čitalnice
Naročanje kopij člankov
Urnik dostave gradiva z oznako DS v signaturi
  • Feature map classifier - a possible approach to morphological/geological evaluation of terrain
    Hafner, Janez, 1966-
    The paper investigates the practicability of new classification approach to image processing. Landsat TM image of Slovene coastal area was used to performlithological classification. Standard ... classification methods, based on statistical principles do not always givee satisfactory results. Therefore a variety of new approaches are being tested in order to achieve better accuracy. One of the most promising fields is artificial intelligence were artificial neural networks have proven to be useful. An artificial neural network represents a limited analogy of the neural functioning of the biological brain. Several ANN methods have been developed to solve classification problems. The one represented in this article is a combination of two methods: Self Organising Maps and Backpropagation network.This kind of ANN, also called Feature Map Classifier, is not the best in sense of accuracy,but has one big advantage in comparison with other ANNs - it is much more transparent.
    Vir: Geologija. - ISSN 0016-7789 (Knj. 46, [št.] 2, 2003, str. 349-360)
    Vrsta gradiva - članek, sestavni del
    Leto - 2003
    Jezik - angleški
    COBISS.SI-ID - 1019477

vir: Geologija. - ISSN 0016-7789 (Knj. 46, [št.] 2, 2003, str. 349-360)

loading ...
loading ...
loading ...

Vnos na polico