Performance analysis of maximum likelihood and artificial neural network classifiers for training sets with mixed pixels

Basit Öğe Kaydı
dc.authoridKAVZOGLU, TASKIN -- 0000-0002-9779-3443; Kavzoglu, Taskin -- 0000-0002-9779-3443
dc.contributor.authorKavzoğlu, Taşkın
dc.contributor.authorReis, Selçuk
dc.date.accessioned13.07.201910:50:10
dc.date.accessioned2019-07-29T19:26:34Z
dc.date.available13.07.201910:50:10
dc.date.available2019-07-29T19:26:34Z
dc.date.issued2008
dc.departmentMühendislik Fakültesi
dc.description.abstractThis study evaluates the performance of an artificial neural network, specifically a multilayer perceptron, and a maximum likelihood algorithm to classify multitemporal Landsat ETM+ remote sensor data. The study area in Turkey is a mountainous region that contains many small scattered fields, usually 5-10 pixels in size. The classifiers were employed to identify eight land cover/use features covering the bulk of the study area using the same training and test datasets in order to avoid any difference resulting from sampling variations. Results show that the neural network approach performed better in extracting land cover information from multi-spectral and multitemporal images with training data sets including a large amount of mixed and atypical pixels. The maximum likelihood classifier was found to be ineffective, particularly in classifying spectrally similar categories and classes having subclasses.
dc.identifier.doi10.2747/1548-1603.45.3.330
dc.identifier.endpage342en_US
dc.identifier.issn1548-1603
dc.identifier.issue3en_US
dc.identifier.scopusqualityQ1
dc.identifier.startpage330en_US
dc.identifier.urihttps://doi.org/10.2747/1548-1603.45.3.330
dc.identifier.urihttps://hdl.handle.net/20.500.12451/5644
dc.identifier.volume45en_US
dc.identifier.wosWOS:000258730900004
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherBellwether Publ Ltd.
dc.relation.ispartofGiscience & Remote Sensing
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.titlePerformance analysis of maximum likelihood and artificial neural network classifiers for training sets with mixed pixels
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
kavzoglu-taskin-2008.pdf
Boyut:
1.24 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

Makale Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu