Kernel based subspace projection of hyperspectral images

Rasmus Larsen; Allan Aasbjerg Nielsen; Morten Arngren; Per Waaben Hansen

Kernel based subspace projection of hyperspectral images

Rasmus Larsen, Allan Aasbjerg Nielsen, Morten Arngren, Per Waaben Hansen

Foss A/S

Research output: Contribution to conference › Poster › Research › peer-review

Abstract

In hyperspectral image analysis an exploratory approach to analyse the image data is to conduct subspace projections. As linear projections often fail to capture the underlying structure of the data, we present kernel based subspace projections of PCA and Maximum Autocorrelation Factors (MAF). The MAF projection exploits the fact that interesting phenomena in images typically exhibit spatial autocorrelation. The analysis is based on nearinfrared hyperspectral images of maize grains demonstrating the superiority of the kernelbased MAF method.

Original language	English
Publication date	2009
Publication status	Published - 2009
Event	2009 European Workshop on Challenges in Modern Massive Data Sets - Technical University of Denmark, Kgs. Lyngby, Denmark Duration: 1 Jul 2009 → 4 Jul 2009

Workshop

Workshop	2009 European Workshop on Challenges in Modern Massive Data Sets
Location	Technical University of Denmark
Country/Territory	Denmark
City	Kgs. Lyngby
Period	01/07/2009 → 04/07/2009

Access to Document

http://www2.imm.dtu.dk/pubdb/views/edoc_download.php/5785/pdf/imm5785.pdf

OpenUrl availability

Full text

Cite this

@conference{50ca2a82bef2432391e7aac8b5844730,

title = "Kernel based subspace projection of hyperspectral images",

abstract = "In hyperspectral image analysis an exploratory approach to analyse the image data is to conduct subspace projections. As linear projections often fail to capture the underlying structure of the data, we present kernel based subspace projections of PCA and Maximum Autocorrelation Factors (MAF). The MAF projection exploits the fact that interesting phenomena in images typically exhibit spatial autocorrelation. The analysis is based on nearinfrared hyperspectral images of maize grains demonstrating the superiority of the kernelbased MAF method.",

author = "Rasmus Larsen and Nielsen, \{Allan Aasbjerg\} and Morten Arngren and Hansen, \{Per Waaben\}",

year = "2009",

language = "English",

note = "2009 European Workshop on Challenges in Modern Massive Data Sets, EMMDS 2009 ; Conference date: 01-07-2009 Through 04-07-2009",

}

TY - CONF

T1 - Kernel based subspace projection of hyperspectral images

AU - Larsen, Rasmus

AU - Nielsen, Allan Aasbjerg

AU - Arngren, Morten

AU - Hansen, Per Waaben

PY - 2009

Y1 - 2009

N2 - In hyperspectral image analysis an exploratory approach to analyse the image data is to conduct subspace projections. As linear projections often fail to capture the underlying structure of the data, we present kernel based subspace projections of PCA and Maximum Autocorrelation Factors (MAF). The MAF projection exploits the fact that interesting phenomena in images typically exhibit spatial autocorrelation. The analysis is based on nearinfrared hyperspectral images of maize grains demonstrating the superiority of the kernelbased MAF method.

AB - In hyperspectral image analysis an exploratory approach to analyse the image data is to conduct subspace projections. As linear projections often fail to capture the underlying structure of the data, we present kernel based subspace projections of PCA and Maximum Autocorrelation Factors (MAF). The MAF projection exploits the fact that interesting phenomena in images typically exhibit spatial autocorrelation. The analysis is based on nearinfrared hyperspectral images of maize grains demonstrating the superiority of the kernelbased MAF method.

M3 - Poster

T2 - 2009 European Workshop on Challenges in Modern Massive Data Sets

Y2 - 1 July 2009 through 4 July 2009

ER -

Kernel based subspace projection of hyperspectral images

Abstract

Workshop

Access to Document

OpenUrl availability

Fingerprint

Cite this