Share Email Print
cover

Proceedings Paper

Images matching based on a new gradient neural network
Author(s): Yan Zhang; Hong-Yan Dong; Zhen-Kang Shen
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Focusing on the searching strategy in image matching, this paper constructs an energy function with features of a convex function based on Lyapunov Stability Theorem. It thus enables the Gradient neural network to converge steadily into the set of critical points of the target function. Then this paper tries to apply the network in image matching with moment invariants as the feature parameter. The specific steps of the experiments are supplied in this paper. According to the results of the experiments, this matching algorithm features good convergence, high speed, wide applicability and an extraordinary matching effect.

Paper Details

Date Published: 24 October 2006
PDF: 8 pages
Proc. SPIE 6357, Sixth International Symposium on Instrumentation and Control Technology: Signal Analysis, Measurement Theory, Photo-Electronic Technology, and Artificial Intelligence, 635709 (24 October 2006); doi: 10.1117/12.716694
Show Author Affiliations
Yan Zhang, National Univ. of Defense Technology (China)
Hong-Yan Dong, National Univ. of Defense Technology (China)
Zhen-Kang Shen, National Univ. of Defense Technology (China)


Published in SPIE Proceedings Vol. 6357:
Sixth International Symposium on Instrumentation and Control Technology: Signal Analysis, Measurement Theory, Photo-Electronic Technology, and Artificial Intelligence
Jiancheng Fang; Zhongyu Wang, Editor(s)

© SPIE. Terms of Use
Back to Top