Title :
A weighted combination of classifiers employing shared and distinct representations
Author :
Kittler, J. ; Hojjatoleslami, S.A.
Author_Institution :
Centre for Vision Speech & Signal Process., Surrey Univ., Guildford, UK
Abstract :
This paper presents a theoretical framework for the combination of soft decisions generated by experts employing mixed (some shared and some distinct) object representations. By taking the confidence of the individuals experts into account, weighted benevolent fusion strategies are derived. This provides a basis for combining classifiers and illustrates that a substantial gain in performance can be achieved by using the opinions of multiple experts. These strategies are experimentally tested and their effectiveness is considered
Keywords :
object recognition; pattern classification; classifiers; distinct representations; object representations; shared representations; soft decisions; weighted benevolent fusion strategies; weighted combination of classifiers; Bayesian methods; Error analysis; Error probability; Fusion power generation; Pattern recognition; Performance gain; Signal generators; Signal processing; Speech processing; Testing;
Conference_Titel :
Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8497-6
DOI :
10.1109/CVPR.1998.698715
