Share Email Print

Proceedings Paper

Spectral dimensionality reduction based on intergrated bispectrum phase for hyperspectral image analysis
Author(s): Khairul Muzzammil Saipullah; Deok-Hwan Kim
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, we propose a method to reduce spectral dimension based on the phase of integrated bispectrum. Because of the excellent and robust information extracted from the bispectrum, the proposed method can achieve high spectral classification accuracy even with low dimensional feature. The classification accuracy of bispectrum with one dimensional feature is 98.8%, whereas those of principle component analysis (PCA) and independent component analysis (ICA) are 41.2% and 63.9%, respectively. The unsupervised segmentation accuracy of bispectrum is also 20% and 40% greater than those of PCA and ICA, respectively.

Paper Details

Date Published: 26 October 2011
PDF: 8 pages
Proc. SPIE 8180, Image and Signal Processing for Remote Sensing XVII, 81801H (26 October 2011); doi: 10.1117/12.899274
Show Author Affiliations
Khairul Muzzammil Saipullah, Univ. Teknikal Malaysia Melaka (Malaysia)
Deok-Hwan Kim, Inha Univ. (Korea, Republic of)

Published in SPIE Proceedings Vol. 8180:
Image and Signal Processing for Remote Sensing XVII
Lorenzo Bruzzone, Editor(s)

© SPIE. Terms of Use
Back to Top