Abstract
Markov Random Field (MRF) models with potentials learned from the data have recently received attention for learning the low-level structure of natural images. A MRF provides a principled model for whole images, unlike ICA, which can in practice be estimated for small patches only. However, learning the filters in an MRF paradigm has been problematic in the past since it required computationally expensive Monte Carlo methods. Here, we show how MRF potentials can be estimated using Score Matching (SM). With this estimation method we can learn filters of size 12 ×12 pixels, considerably larger than traditional ”hand-crafted” MRF potentials. We analyze the tuning properties of the filters in comparison to ICA filters, and show that the optimal MRF potentials are similar to the filters from an overcomplete ICA model.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Roth, S., Black, M.: Fields of experts: A framework for learning image priors. In: CVPR, vol. 2, pp. 860–867 (2005)
Woodford, O., Reid, I., Torr, P., Fitzgibbon, A.: Fields of experts for image-based rendering. In: Proceedings British Machine Vision Conference (2006)
Zhu, S., Wu, Y., Mumford, D.: FRAME: Filters, random field and maximum entropy – towards a unified theory for texture modeling. International Journal of Computer Vision 27(2), 1–20 (1998)
van Hateren, J.H., van der Schaaf, A.: Independent component filters of natural images compared with simple cells in primary visual cortex. Proc. R. Soc. Lond. B 265, 359–366 (1998)
Li, S.Z.: Markov Random Field modelling in image analysis, 2nd edn. Springer, Heidelberg (2001)
Comon, P.: Independent component analysis – a new concept? Signal Processing 36, 287–314 (1994)
Hyvärinen, A.: Estimation of non-normalized statistical models using score matching. Journal of Machine Learning Research 6, 695–709 (2005)
Atick, J.: Could information theory provide an ecological theory of sensory processing? Network: Computation in neural systems 3, 213–251 (1992)
Hyvärinen, A., Hoyer, P., Inki, M.: Topographic independent component analysis. Neural Computation (2001)
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771–1800 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Köster, U., Lindgren, J.T., Hyvärinen, A. (2009). Estimating Markov Random Field Potentials for Natural Images. In: Adali, T., Jutten, C., Romano, J.M.T., Barros, A.K. (eds) Independent Component Analysis and Signal Separation. ICA 2009. Lecture Notes in Computer Science, vol 5441. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-00599-2_65
Download citation
DOI: https://doi.org/10.1007/978-3-642-00599-2_65
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-00598-5
Online ISBN: 978-3-642-00599-2
eBook Packages: Computer ScienceComputer Science (R0)