Share Email Print
cover

Proceedings Paper

Intensity-invariant recognition, vector spaces and camouflage
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

From the point of view of vector spaces, intensity invariant pattern recognition corresponds to identifying vectors independently of their length, which means that such methods consist primarily on measuring angles between vectors in vector spaces. We describe a few such methods that have proven to be efficient for various intensity variations of targets in unsegmented natural scenes. The conventional wisdom for camouflage states that the best camouflage is one that breaks up the lines of objects, so most camouflage schemes are binary. We discuss the best methods of detecting such camouflage objects in natural scenes.

Paper Details

Date Published: 21 October 2004
PDF: 6 pages
Proc. SPIE 5622, 5th Iberoamerican Meeting on Optics and 8th Latin American Meeting on Optics, Lasers, and Their Applications, (21 October 2004); doi: 10.1117/12.591671
Show Author Affiliations
Henri H. Arsenault, Univ. Laval (Canada)
Pascuala Garcia-Martinez, Univ. de Valencia (Spain)


Published in SPIE Proceedings Vol. 5622:
5th Iberoamerican Meeting on Optics and 8th Latin American Meeting on Optics, Lasers, and Their Applications
Aristides Marcano O.; Jose Luis Paz, Editor(s)

© SPIE. Terms of Use
Back to Top