Feature reduction of hyperspectral imagery using hybrid wavelet-principal component analysis

Sinthop Kaewpijit; Jacqueline Le Moigne; Tarek El-Ghazawi

doi:10.1117/1.1637907

1 February 2004 Feature reduction of hyperspectral imagery using hybrid wavelet-principal component analysis

Sinthop Kaewpijit, Jacqueline Le Moigne, Tarek El-Ghazawi

Optical Engineering, Vol. 43, Issue 2, (February 2004). https://doi.org/10.1117/1.1637907

Hyperspectral imagery can provide very valuable information on land cover classes. However, it also presents many challenges in data analysis and interpretation as a result of the large amounts of data collected. For example, conventional methods for land use and land cover classifications may not be directly applicable. Such conventional methods typically require a preprocessing step to transform high dimensional data to a lower dimension, mostly by eliminating data redundancy. For decades, principal component analysis (PCA) has been widely used to decorrelate spectral bands for reducing dimensionality. It is a useful technique if the spectral class structure of the transformed data is distributed along the first few axes. Otherwise, the transformed data may be similar to the original data. In such cases, we have shown in an earlier work that the wavelet decomposition technique is a better approach. Wavelet decomposition can reduce hyperspectral data in the spectral domain for each pixel. By carefully combining PCA and wavelet techniques, we engender a new method that benefits from the strength of both techniques. The intent of the hybrid method is to provide a tradeoff between the accuracy and speed, as compared with PCA and wavelet methods. The effectiveness of this method is demonstrated by using hyperspectral data from the Airborne Visible Infrared Imaging Spectrometer (AVIRIS) hyperspectral instrument. The experimental results show that, for high reduction rates, the hybrid method is superior to pure PCA and to pure wavelet-based techniques.

©(2004) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Sinthop Kaewpijit, Jacqueline Le Moigne, and Tarek El-Ghazawi "Feature reduction of hyperspectral imagery using hybrid wavelet-principal component analysis," Optical Engineering 43(2), (1 February 2004). https://doi.org/10.1117/1.1637907

Published: 1 February 2004

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available