Share Email Print
cover

Proceedings Paper

Detection of objects composed of several regions using maximum likelihood based filters
Author(s): Javier Garcia; Vincent Page; Philippe Refregier
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The detection of objects composed of several regions by means of maximum likelihood based filters is analyzed. The target is assumed to have different unknown mean values in each of its regions. First, the cases where the number of actual distinct regions is known is considered. Also, we analyze the cases when an estimation of the actual configuration of the mean values in the target region is needed. A simplified filter that reduces the computational complexity is also proposed. The statistical performance is theoretically analyzed and tested in computer experiments dealing with real images.

Paper Details

Date Published: 19 November 2003
PDF: 2 pages
Proc. SPIE 4829, 19th Congress of the International Commission for Optics: Optics for the Quality of Life, (19 November 2003); doi: 10.1117/12.524814
Show Author Affiliations
Javier Garcia, Univ. de Valencia (Spain)
Vincent Page, Ecole Nationale Superieure de Physique de Marseille (France)
Philippe Refregier, Ecole Nationale Superieure de Physique de Marseille (France)


Published in SPIE Proceedings Vol. 4829:
19th Congress of the International Commission for Optics: Optics for the Quality of Life
Giancarlo C. Righini; Anna Consortini, Editor(s)

© SPIE. Terms of Use
Back to Top