Class specific redundancies in natural images: a theory of extrastriate visual processing

Authors:
Mohsen Malmir;Saeed Shiry
Affiliations:
Department of Computer Engineering, Amirkabir University of Technology, Tehran Polytechnic, Tehran, Iran;Department of Computer Engineering, Amirkabir University of Technology, Tehran Polytechnic, Tehran, Iran
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 9
Cited 1

What is the goal of sensory coding?

Neural Computation
Hierarchical models of variance sources

Signal Processing - Special issue on independent components analysis and beyond
A Hierarchical Bayesian Model for Learning Nonlinear Statistical Regularities in Nonstationary Natural Signals

Neural Computation
Topographic Independent Component Analysis

Neural Computation
Soft Mixer Assignment in a Hierarchical Generative Model of Natural Scene Statistics

Neural Computation
Sparse approximation of images inspired from the functional architecture of the primary visual areas

EURASIP Journal on Applied Signal Processing
Review:

Journal of Cognitive Neuroscience
Image compression via joint statistical characterization in the wavelet domain

IEEE Transactions on Image Processing
Image denoising using scale mixtures of Gaussians in the wavelet domain

IEEE Transactions on Image Processing

Object recognition with statistically independent features: a model inspired by the primate visual cortex

RoboCup 2009

Quantified Score

Hi-index	0.00

Visualization

Abstract

Statistical properties of natural signals is an important factor in forming neuronal selectivities of brain sensory system. One such property is the redundancy in visual and auditory inputs to the brain. In this paper, we introduce the concept of class specific redundancies in natural images and propose that the selectivity of neurons in extrastriate visual areas is developed to reveal these redundancies. In each extrastriate area, a redundancy reduction mechanism removes these revealed redundancies to provide a more efficient representation of the input image. To test this hypothesis, we implemented a model of area V2 and trained this model with a set of natural images. Experiments on artificial stimulus sets and natural images show the close similarity of model neurons to real V2 neurons and their preference for coding object contours over textures.