A Comparison of Hierarchical Classification Processes Based on Hyperspectral Image

Author

Kuo, Bor-Chen ; Hung, Chih-Cheng ; Chi, Ming-Hung ; Hsieh, Tien-Yu

Author_Institution

Grad. Sch. of Educ. Meas. & Stat., Nat. Taichung Univ., Taichung

fYear

2006

fDate

July 31 2006-Aug. 4 2006

Firstpage

948

Lastpage

951

Abstract

In this study, the performances of hyperspectral image classification using three max-cut based BHC schemes are compared. The first one is original BHC scheme and the second is applied feature extraction in the root node. The last is applied feature extraction in the each non-leaf node. The real data experimental results show that applying feature extraction in the each non-leaf node is the best strategy. Among the combinations of two feature extraction methods, DAFE and NWFE and three base classifiers, using NWFE and ML base classifier can reach the best performance.

Keywords

feature extraction; geophysics computing; image classification; discriminant analysis feature extraction; hierarchical classification processes; hyperspectral image; max-cut based BHC schemes; maximal likelihood base classifier; nonleaf node; nonparametric weighted feature extraction; root node; Data mining; Feature extraction; Hierarchical systems; Hyperspectral imaging; Image classification; Performance evaluation; Software measurement; Statistics; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2006. IGARSS 2006. IEEE International Conference on

Conference_Location

Denver, CO

Print_ISBN

0-7803-9510-7

Type

conf

DOI

10.1109/IGARSS.2006.244

Filename

4241391