A combination of k-means clustering and entropy filtering for band selection and classification in hyperspectral images

Autor(es)

Santos, A. C. S. ; Pedrini, H.

• Tipo de documento: Artigo Científico
• Fonte: International Journal of Remote Sensing; v. 37, n. 13, p. 3005-3020, 2016.
• Citações Web of Science: 5

Resumo

Hyperspectral images usually have large volumes of data comprising hundreds of spectral bands. Removal of redundant bands can both reduce computational time and improve classification performance. This work proposes and analyses a band-selection method based on the k-means clustering strategy combined with a classification approach using entropy filtering. Experimental results in different terrain images show that our method can significantly reduce the number of bands while maintaining an accurate classification. (AU)

• Processo FAPESP: 11/22749-8 - Desafios em visualização exploratória de dados multidimensionais: novos paradigmas, escalabilidade e aplicações
• Beneficiário: Luis Gustavo Nonato
• Linha de fomento: Auxílio à Pesquisa - Temático