Image sequence correspondence via a Hopfield neural network

Jyh-Yeong Chang; Shin-Wen Lee; Mong-Fong Horng

doi:10.1117/12.139811

1 July 1993 Image sequence correspondence via a Hopfield neural network

Jyh-Yeong Chang, Shin-Wen Lee, Mong-Fong Horng

Author Affiliations +

Optical Engineering, Vol. 32, Issue 7, (July 1993). https://doi.org/10.1117/12.139811

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.

Citation Download Citation

Jyh-Yeong Chang, Shin-Wen Lee, and Mong-Fong Horng "Image sequence correspondence via a Hopfield neural network," Optical Engineering 32(7), (1 July 1993). https://doi.org/10.1117/12.139811

Published: 1 July 1993

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available