ICA 2007

ICA 2007
7th International Conference on
Independent Component Analysis
and Signal Separation

London, UK        9 - 12 September 2007

Banner showing images of London
- Home
- Committee
- Call for Papers
- Submission
- Info for Presenters
- Dates
- Programme
- Tutorials
- Keynotes
- Papers
- Registration
- Accommodation
- Venue
- Maps
- Arrival
- Travel Tips
- Links
- Contact

Paper No: 113

Bayesian Estimation of Overcomplete Independent Feature Subspaces for Natural Images

Author(s): Libo Ma, Liqing Zhang, Wenlu Yang

Abstract

In this paper, we propose a Bayesian estimation approach to extend independent subspace analysis (ISA) for an overcomplete representation without imposing the orthogonal constraint. Our method is based on a synthesis of ISA [1] and overcomplete independent component analysis [2] developed by Hyvärinen et al. By introducing the variables of dot products (between basis vectors and whitened observed data vectors), we investigate the energy correlations of dot products in each subspace. Based on the prior probability of quasi-orthogonal basis vectors, the MAP (maximum a posteriori) estimation method is used for learning overcomplete independent feature subspaces. A gradient ascent algorithm is derived to maximize the posterior probability of the mixing matrix. Simulation results on natural images demonstrate that the proposed model can yield overcomplete independent feature subspaces and the emergence of phase- and limited shift-invariant features--the principal properties of visual complex cells.

Last Updated: 14-Aug-2007   Please read our disclaimer