Abstract

In applications of principal component analysis (PCA) it has often been observed that the eigenvector with the largest eigenvalue has only nonnegative entries when the vectors of the underlying stochastic process have only nonnegative values. This has been used to show that the coordinate vectors in PCA are all located in a cone. We prove that the nonnegativity of the first eigenvector follows from the Perron–Frobenius (and Krein–Rutman theory). Experiments show also that for stochastic processes with nonnegative signals the mean vector is often very similar to the first eigenvector. This is not true in general, but we first give a heuristical explanation why we can expect such a similarity. We then derive a connection between the dominance of the first eigenvalue and the similarity between the mean and the first eigenvector and show how to check the relative size of the first eigenvalue without actually computing it. In the last part of the paper we discuss the implication of theoretical results for multispectral color processing.

© 2005 Optical Society of America

Unsupervised filtering of color spectra

Reiner Lenz, Mats Österberg, Jouni Hiltunen, Timo Jaaskelainen, and Jussi Parkkinen
J. Opt. Soc. Am. A 13(7) 1315-1324 (1996)

Eigenvectors of optimal color spectra

Mika Flinkman, Hannu Laamanen, Jukka Tuomela, Pasi Vahimaa, and Markku Hauta-Kasari
J. Opt. Soc. Am. A 30(9) 1806-1813 (2013)

Uniform color spaces and natural image statistics

Kyle C. McDermott and Michael A. Webster
J. Opt. Soc. Am. A 29(2) A182-A187 (2012)

Characteristic spectra of Munsell colors

J. P. S. Parkkinen, J. Hallikainen, and T. Jaaskelainen
J. Opt. Soc. Am. A 6(2) 318-322 (1989)

Eigenvector interpretation of the Farnsworth–Munsell 100-hue test

K. Mantere, J. Parkkinen, M. Mäntyjärvi, and T. Jaaskelainen
J. Opt. Soc. Am. A 12(10) 2237-2243 (1995)