標題: APPLYING OPTIMAL ALGORITHM TO DATA-DEPENDENT KERNEL FOR HYPERSPECTRAL IMAGE CLASSIFICATION
作者: Chen, I-Ling
Li, Cheng-Hsuan
Kuo, Bor-Chen
Huang, Hsiao-Yun
電控工程研究所
Institute of Electrical and Control Engineering
關鍵字: Kernel optimization;Support vector machine;Fisher criteria;Feature space
公開日期: 2010
摘要: In the kernel methods, it is very important to choose a proper kernel function to avoid overlapping data. Based this fact, in this paper we mainly utilize a unified kernel optimization framework on the hyperspectral image classification to augment the margin between different classes, and under the kernel optimization framework, to employ the Fisher discriminant criteria formulated in a pairwise manner as the objective functions to optimize the kernel function in Kernel-based nonparametric weighted feature extraction. The experimental results display the superiority of the optimizing kernel function over the RBF kernel function with 5-fold cross-validation method, especially, in the small sample size problem.
URI: http://dx.doi.org/10.1109/IGARSS.2010.5654477
http://hdl.handle.net/11536/134851
ISBN: 978-1-4244-9566-5
ISSN: 2153-6996
DOI: 10.1109/IGARSS.2010.5654477
期刊: 2010 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM
起始頁: 2808
結束頁: 2811
Appears in Collections:Conferences Paper