@inproceedings{211a1fd9de3f440cbca57695d52b2a38,
title = "Feature extraction for hyperspectral image cubes by noise-adjusted canonical analysis",
abstract = "This paper develops a novel approach that embeds minimum noise fraction (or noise-adjusted principal component analysis) in canonical analysis (called noise-adjusted canonical analysis, NACA). The objective is to take the discriminability of targets and quality of image into account simultaneously when extracting features from hyperspectral image data sets. Experimental results indicate that the NACA algorithm for classification task can produce better results than principal component analysis, conventional canonical analysis and minimum noise fraction from an airborne and an EO-1 Hyperion image data.",
keywords = "Canonical analysis, Minimum noise fraction, Noise-adjusted canonical analysis, Principal component analysis",
author = "Lai, {Jhe Syuan} and Fuan Tsai",
year = "2012",
language = "???core.languages.en_GB???",
isbn = "9781622769742",
series = "33rd Asian Conference on Remote Sensing 2012, ACRS 2012",
pages = "628--635",
booktitle = "33rd Asian Conference on Remote Sensing 2012, ACRS 2012",
note = "33rd Asian Conference on Remote Sensing 2012, ACRS 2012 ; Conference date: 26-11-2012 Through 30-11-2012",
}