Combining: an alternative for choosing between reject-first and accept-first classifiers

Author

Mascarilla, Laurent ; Frélicot, Carl ; Zahzah, El-Hadi

Author_Institution

Lab. d´´Inf. et d´´Imagerie Ind., Univ. de la Rochelle, France

fYear

1999

fDate

36342

Firstpage

253

Lastpage

257

Abstract

In the general framework of pattern classification two reject strategies are identified. These classifiers are defined as a couple of labeling and hardening functions. In this paper the first stage of classifiers belonging to each strategy are used in turn and their results are combined with a Dempster-Shafer model to classify or reject patterns. Results on artificial data are provided

Keywords

inference mechanisms; pattern classification; uncertainty handling; Dempster-Shafer model; accept-first classifiers; hardening function; labeling function; pattern classification; reject strategies; reject-first classifiers; uncertainty handling; Labeling; Mathematical model; Pattern classification; Pattern matching; Reliability theory; Testing; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Information Processing Society, 1999. NAFIPS. 18th International Conference of the North American

Conference_Location

New York, NY

Print_ISBN

0-7803-5211-4

Type

conf

DOI

10.1109/NAFIPS.1999.781693

Filename

781693

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3025411