ICA FEATURES OF COLOUR AND STEREO IMAGES
Patrik O. Hoyer and Aapo Hyv#rinen
Previous work has shown that independent component
analysis (ICA) applied to natural image data yields fea
tures resembling Gabor functions and simplecell recep
tive øelds. This article considers the eoeects of includ
ing chromatic and stereo information. The inclusion of
colour leads to features divided into separate red/green,
blue/yellow, and bright/dark channels. Stereo image
data, on the other hand, leads to binocular receptive
øelds which are tuned to various disparities. The sim
ilarities between these results and observed properties
of simple cells in primary visual cortex are further ev
idence for the hypothesis that visual cortical neurons
perform some type of redundancy reduction, which was
one of the original motivations for ICA in the ørst
place. In addition, ICA provides a principled method
for feature extraction from colour and stereo images;
such features could be used in image processing op
erations such as denoising, compression, and pattern
recognition.