loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
18th International Conference on Pattern Recognition (ICPR'06) Volume 2
Adaptive Step Size Window Matching for Detection
Hong Kong
August 20-August 24
ISBN: 0-7695-2521-0
Nathan Mekuz, York University, Toronto, ON, Canada
Konstantinos G. Derpanis, York University, Toronto, ON, Canada
John K. Tsotsos, York University, Toronto, ON, Canada
An often overlooked problem in matching lies in selecting an appropriate step size. The selection of the step size for real-time applications is critical both from the point of view of computational efficiency and detection performance. Current systems set the step size in an ad hoc manner. This paper describes an algorithm for selecting the step size based on a theoretical worst case analysis. We have implemented this adaptive step size method in an object detection algorithm. Experimental evaluation demonstrates the effectiveness of our proposed algorithm.
Citation:
Nathan Mekuz, Konstantinos G. Derpanis, John K. Tsotsos, "Adaptive Step Size Window Matching for Detection," icpr, vol. 2, pp.259-262, 18th International Conference on Pattern Recognition (ICPR'06) Volume 2, 2006
Usage of this product signifies your acceptance of the Terms of Use.