Title :
A third way to design pattern classifiers with reject options
Author :
Frélicot, Carl ; Mascarilla, Laurent
Author_Institution :
Comput. Vision Lab., Univ. of La Rochelle, France
Abstract :
The design of a rejection-based classifier can be made according to two well-identified strategies operating in two sequential steps: the accept-first strategy and the reject-first one. The first one is the most usual. Recently, we have proposed a general class of the latter classifiers using fuzzy XOR operators based on dual triples (t-norm, t-conorm, complement) (2001). In this paper, we investigate a new approach. It consists in starting with testing for ambiguity rejection, and if needed, testing for either exclusive classification or distance rejection. For this purpose, we define a new operator called the fuzzy OR-2 allowing us to propose a new class of classifiers.
Keywords :
fuzzy logic; pattern classification; accept-first; ambiguity rejection; distance rejection; exclusive classification; fuzzy OR-2; fuzzy XOR operators; reject-first; rejection-based classifier; sequential steps; Bayesian methods; Computer vision; Hypercubes; Labeling; Laboratories; Large Hadron Collider; Linear predictive coding; Pattern classification; Presses; Testing;
Conference_Titel :
Fuzzy Information Processing Society, 2002. Proceedings. NAFIPS. 2002 Annual Meeting of the North American
Print_ISBN :
0-7803-7461-4
DOI :
10.1109/NAFIPS.2002.1018092