Kernel based subspace projection of near infrared hyperspectral images of maize kernels 
Rasmus Larsen, Morten Arngren, Per Waaben Hansen, Allan Aasbjerg Nielsen

Abstract  In this paper we present an exploratory analysis of hyper
spectral 9001700 nm images of maize kernels. The imaging device is
a line scanning hyper spectral camera using a broadband NIR illumi
nation. In order to explore the hyperspectral data we compare a series
of subspace projection methods including principal component analysis
and maximum autocorrelation factor analysis. The latter utilizes the fact
that interesting phenomena in images exhibit spatial autocorrelation.
However, linear projections often fail to grasp the underlying variability
on the data. Therefore we propose to use socalled kernel version of the
two aforementioned methods. The kernel methods implicitly transform
the data to a higher dimensional space using nonlinear transformations
while retaining the computational complexity. Analysis on our data ex
ample illustrates that the proposed kernel maximum autocorrelation fac
tor transform outperform the linear methods as well as kernel principal
components in producing interesting projections of the data. 
Keywords  Kernel methods, maximum autocorrelation factor, principal components 
Type  Conference paper [With referee] 
Conference  Proceesings of the 16th Scandinavian Conference on Image Analysis 
Editors  
Year  2009 Vol. 5575 pp. 560569 
Publisher  Springer 
Address  Heidelberg 
Series  Lecture Notes in Computer Science 
Electronic version(s)  [pdf] 
BibTeX data  [bibtex] 
IMM Group(s)  Image Analysis & Computer Graphics 