PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

The "Tree-Dependent Components" of Natural Images are Edge Filters
Daniel Zoran and Yair Weiss
Advances in Neural Information Processing Systems (NIPS) 2009.

Abstract

We propose a new model for natural image statistics. Instead of minimizing dependency between components of natural images, we maximize a simple form of dependency in the form of tree-dependencies. By learning filters and tree structures which are best suited for natural images we observe that the resulting filters are edge filters, similar to the famous ICA on natural images results. Calculating the likelihood of an image patch using our model requires estimating the squared output of pairs of filters connected in the tree. We observe that after learning, these pairs of filters are predominantly of similar orientations but different phases, so their joint energy resembles models of complex cells.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Machine Vision
Learning/Statistics & Optimisation
ID Code:5635
Deposited By:Talya Meltzer
Deposited On:08 March 2010