On the connection between the human visual system and independent component analysis

Authors:
Susana Hornillo-Mellado;Rubén Martín-Clemente;Carlos G. Puntonet;José I. Acha
Affiliations:
Dpto. de Teoría de la Señal y Comunicaciones, Escuela Superior de Ingenieros, Universidad de Sevilla, Sevilla, Spain;Dpto. de Teoría de la Señal y Comunicaciones, Escuela Superior de Ingenieros, Universidad de Sevilla, Sevilla, Spain;Dpto. de Arquitectura y Tecnología de Computadores, E.T.S. de Ingeniería Informática, Universidad de Granada, Granada, Spain;Dpto. de Teoría de la Señal y Comunicaciones, Escuela Superior de Ingenieros, Universidad de Sevilla, Sevilla, Spain
Venue:
IWINAC'05 Proceedings of the First international work-conference on the Interplay Between Natural and Artificial Computation conference on Artificial Intelligence and Knowledge Engineering Applications: a bioinspired approach - Volume Part II
Year:
2005

Citing 5
Cited 0

What is the goal of sensory coding?

Neural Computation
A fast fixed-point algorithm for independent component analysis

Neural Computation
Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications

Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications
Application of Independent Component Analysis to Edge Detection and Watermarking

IWANN '03 Proceedings of the 7th International Work-Conference on Artificial and Natural Neural Networks: Part II: Artificial Neural Nets Problem Solving Methods
General approach to blind source separation

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Human Visual System (HVS) presents some properties that are shared by the results obtained when Independent Component Analysis (ICA) is applied to natural images. Particularly, the special appearance of the ICA bases (they look like “edges”) and the sparse distribution of the independent components have been linked to the receptive fields of the simple neurons in the visual cortex and their way to codify the visual information, respectively. Nevertheless, no theoretical study has been provided so far to explain that behaviour of ICA. The objective of this paper is to analyze, both mathematical and experimentally, the results obtained when ICA is applied to natural images in order to supply a theoretical basis for the connection between ICA and the HVS.