Learning High-level Independent Components of Images through a Spectral Representation
Jussi Lindgren and Aapo Hyvärinen
In: ICPR 2004, 23-26 Aug 2004, Cambridge, UK.
Statistical methods, such as independent component analysis, have
been successful in learning local low-level features from natural
image data. Here we extend these methods for learning high-level
representations of whole images or scenes. We show empirically
that independent component analysis is able to capture some
intuitive natural image categories when applied on histograms of
outputs of ordinary Gabor-like filters. This can be taken as an
indication that maximizing the independence or sparseness of
features may be a meaningful strategy even on higher levels of
image processing, for such advanced functionality as object
recognition or image retrieval from databases.