Table of Contents
ISRN Machine Vision
Volume 2013 (2013), Article ID 138057, 10 pages
http://dx.doi.org/10.1155/2013/138057
Research Article

Active Object Recognition with a Space-Variant Retina

Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA 91109, USA

Received 6 October 2013; Accepted 24 October 2013

Academic Editors: H. Erdogan, O. Ghita, D. Hernandez, A. Nikolaidis, and J. P. Siebert

Copyright © 2013 Christopher Kanan. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

When independent component analysis (ICA) is applied to color natural images, the representation it learns has spatiochromatic properties similar to the responses of neurons in primary visual cortex. Existing models of ICA have only been applied to pixel patches. This does not take into account the space-variant nature of human vision. To address this, we use the space-variant log-polar transformation to acquire samples from color natural images, and then we apply ICA to the acquired samples. We analyze the spatiochromatic properties of the learned ICA filters. Qualitatively, the model matches the receptive field properties of neurons in primary visual cortex, including exhibiting the same opponent-color structure and a higher density of receptive fields in the foveal region compared to the periphery. We also adopt the “self-taught learning” paradigm from machine learning to assess the model’s efficacy at active object and face classification, and the model is competitive with the best approaches in computer vision.