Share Email Print
cover

Proceedings Paper

A new bandwidth selection criterion for using SVDD to analyze hyperspectral data
Author(s): Yuwei Liao; Deovrat Kakde; Arin Chaudhuri; Hansi Jiang; Carol Sadek; Seunghyun Kong
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper presents a method for hyperspectral image classification that uses support vector data description (SVDD) with the Gaussian kernel function. SVDD has been a popular machine learning technique for single-class classification, but selecting the proper Gaussian kernel bandwidth to achieve the best classification performance is always a challenging problem. This paper proposes a new automatic, unsupervised Gaussian kernel bandwidth selection approach which is used with a multiclass SVDD classification scheme. The performance of the multiclass SVDD classification scheme is evaluated on three frequently used hyperspectral data sets, and preliminary results show that the proposed method can achieve better performance than published results on these data sets.

Paper Details

Date Published: 8 May 2018
PDF: 12 pages
Proc. SPIE 10644, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXIV, 106441M (8 May 2018); doi: 10.1117/12.2314964
Show Author Affiliations
Yuwei Liao, SAS Institute Inc. (United States)
Deovrat Kakde, SAS Institute Inc. (United States)
Arin Chaudhuri, SAS Institute Inc. (United States)
Hansi Jiang, SAS Institute Inc. (United States)
Carol Sadek, SAS Institute Inc. (United States)
Seunghyun Kong, SAS Institute Inc. (United States)


Published in SPIE Proceedings Vol. 10644:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXIV
Miguel Velez-Reyes; David W. Messinger, Editor(s)

© SPIE. Terms of Use
Back to Top