Morphological sampling based on foveal mechanisms

Research realized in the field of human vision offers a tremendous potential for computer vision. In our opinion, if we are expected to write algorithms and to build models for image processing, it is necessary to take into account some features of the organization of the human visual system. In tha...

Full description

Saved in:
Bibliographic Details
Main Authors: Dinet, E, Laget, B
Format: Conference Proceeding
Language:English
Subjects:
Applied sciences
Artificial intelligence
Computer science
control theory
systems
Computer vision and image processing techniques
Exact sciences and technology
Optical information, image and video signal processing
Pattern recognition. Digital image processing. Computational geometry
Physiology of the eye
nerve structure and function
Psychophysics of vision, visual perception, binocular vision
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Research realized in the field of human vision offers a tremendous potential for computer vision. In our opinion, if we are expected to write algorithms and to build models for image processing, it is necessary to take into account some features of the organization of the human visual system. In that way we have chosen to base our investigation on the retina. Indeed the retina is the first neuronal structure involved in visual perception and it is largely studied by neurobiologists as mentioned by Wandell (1995). One goal of this paper is to show how the knowledge of a particular organ implied in vision can be used to conceive new sampling operators (space-variant and morphological) to realize selective analysis of a scene.
ISSN:0537-9989
DOI:10.1049/cp:19971006