Share Email Print

Proceedings Paper

Learning of boundary patterns to recognize the gradually changed patterns within the boundary
Author(s): Chia-Lun John Hu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

If the binary image pattern, e.g., the edge-detected boundary of an object, is varying in real time among several extreme boundaries, then learning just the extreme boundaries by an OLNN (one-layered neural network) will allow the OLNN to recognize any unlearned, time-varying patterns of the object varying among these extreme boundaries. This is possible because of the unique property of CONVEX LEARNING existing in the OLNN. This paper will first derive this property from mathematical point of view, and then verify it with some simple experiments. The main advantage of this neural network is that it can recognize very similar objects not only from the static patterns it learns but also from the ways how these objects vary in real time even these varying patterns are NOT learned one by one at each time. Consequently the recognition is much more accurate than just learning the static patterns alone.

Paper Details

Date Published: 19 May 2005
PDF: 8 pages
Proc. SPIE 5807, Automatic Target Recognition XV, (19 May 2005); doi: 10.1117/12.602471
Show Author Affiliations
Chia-Lun John Hu, Southern Illinois Univ./Carbondale (United States)

Published in SPIE Proceedings Vol. 5807:
Automatic Target Recognition XV
Firooz A. Sadjadi, Editor(s)

© SPIE. Terms of Use
Back to Top