Pregled bibliografske jedinice broj: 32731
Multispectral classification of landsat TM images by neural networks
Multispectral classification of landsat TM images by neural networks // International archives of photogrammetry and remote sensing, 32 (1998), 7; 376-382 (podatak o recenziji nije dostupan, članak, znanstveni)
CROSBI ID: 32731 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Multispectral classification of landsat TM images by neural networks
Autori
Marčić, Ivan ; Ribarić, Slobodan ; Kušan, Vladimir
Izvornik
International archives of photogrammetry and remote sensing (0256-1840) 32
(1998), 7;
376-382
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
neural network ; back-propagation ; classification ; multispectral images ; remote sensing ; landsat TM
Sažetak
This work presents the results of experiments with the use of artificial neural networks for land cover classification. The goal of this research was to examine the operation of back-propagation neural network and its application in the classification of remotly sensed data. A back-propagation network with one hidden layer is used to classify a Landsat TM image. The results are compared to Gaussian maximum likelihood classifier. We show that neural network is better in performing than the maximum likelihood classifier.
Izvorni jezik
Engleski
Znanstvena područja
Biotehnologija
POVEZANOST RADA
Projekti:
068002
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb,
Fakultet šumarstva i drvne tehnologije
Profili:
Slobodan Ribarić
(autor)