Paper
1 March 1991 Generalization of the problem of correspondence in long-range motion and the proposal for a solution
Norman A. Stratton, Lucia M. Vaina
Author Affiliations +
Abstract
One of the fundamental problems in vision is the problem of finding the correspondence between two images. This paper addressed this problem in terms of a computational model consistent with existing models of human vision and human visual psychophysics. At the heart of the model is a multi-dimensional internal representation of the input image. We propose that correspondence may be computed by minimizing the total, non- euclidean distance between corresponding elements. A backpropagation programmed neural network is used to investigate the nature of the internal representation.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Norman A. Stratton and Lucia M. Vaina "Generalization of the problem of correspondence in long-range motion and the proposal for a solution", Proc. SPIE 1468, Applications of Artificial Intelligence IX, (1 March 1991); https://doi.org/10.1117/12.45464
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Spatial frequencies

Motion models

Visual process modeling

Visualization

Computing systems

Evolutionary algorithms

Reliability

Back to Top