PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Learning high-order MRF priors of color images
Julian McAuley, Tiberio Caetano, Alex Smola and Matthias Franz
In: ICML 2006, 25-29 Jun 2006, Pittsburgh, USA.


In this paper, we use large neighborhood Markov random fields to learn rich prior models of color images. Our approach extends the monochromatic Fields of Experts model (Roth & Black, 2005a) to color images. In the Fields of Experts model, the curse of dimensionality due to very large clique sizes is circumvented by parameterizing the potential functions according to a product of experts. We introduce simplifications to the original approach by Roth and Black which allow us to cope with the increased clique size (typically 3x3x3 or 5x5x3 pixels) of color images. Experimental results are presented for image denoising which evidence improvements over state-of-the-art monochromatic image priors.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:5542
Deposited By:Julian McAuley
Deposited On:25 February 2010