Share Email Print

Optical Engineering

Image sequence correspondence via a Hopfield neural network
Author(s): Jyh-Yeong Chang; Shin-Wen Lee; Mong-Fong Horng
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A neural network approach to finding trajectories of feature points in a monocular image sequence is proposed. In conventional methods, this problem is formulated as an optimization problem and solved using heuristic algorithms. The problem usually involves lengthy computations, making it computationally difficult. We apply the Hopfield neural network to image sequence correspondence. The design and development of the Lyapunov function for this problem are discussed in detail. Furthermore, the neural-network-based image correspondence scheme is extended to the case of successive image frames, in which some feature points are allowed to be occluded. Examples and simulation results are presented to illustrate the design process and the convergence characteristics of the proposed neural network. By using the massive parallel-processing power of neural networks, a real-time and accurate solution can be obtained.

Paper Details

Date Published: 1 July 1993
PDF: 8 pages
Opt. Eng. 32(7) doi: 10.1117/12.139811
Published in: Optical Engineering Volume 32, Issue 7
Show Author Affiliations
Jyh-Yeong Chang, National Chiao-Tung Univ. (Taiwan)
Shin-Wen Lee, Industrial Techology Research Institute (Taiwan)
Mong-Fong Horng, Nation Chiao Tung Univ. (Taiwan)

© SPIE. Terms of Use
Back to Top