Title :
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
fDate :
July 31 2006-Aug. 4 2006
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;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2006. IGARSS 2006. IEEE International Conference on
Conference_Location :
Denver, CO
Print_ISBN :
0-7803-9510-7
DOI :
10.1109/IGARSS.2006.244