Fuzziness-based active learning framework to enhance hyperspectral image classification performance for discriminative and generative classifiers

Hyperspectral image classification with a limited number of training samples without loss of accuracy is desirable, as collecting such data is often expensive and time-consuming. However, classifiers trained with limited samples usually end up with a large generalization error. To overcome the said...

Ful tanımlama

Kaydedildi:
Detaylı Bibliyografya
Yayımlandı:PLoS One
Asıl Yazarlar: Ahmad, Muhammad, Protasov, Stanislav, Khan, Adil Mehmood, Hussain, Rasheed, Khattak, Asad Masood, Khan, Wajahat Ali
Materyal Türü: Artigo
Dil:Inglês
Baskı/Yayın Bilgisi: Public Library of Science 2018
Konular:
Research Article
Online Erişim:https://ncbi.nlm.nih.gov/pmc/articles/PMC5756090/
https://ncbi.nlm.nih.gov/pubmed/29304512
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1371/journal.pone.0188996
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!

Benzer Materyaller