A Cascaded Multiple Expert System for Verification

Authors:
Luigi P. Cordella;Pasquale Foggia;Carlo Sansone;Francesco Tortorella;Mario Vento
Affiliations:
-;-;-;-;-
Venue:
MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
Year:
2000

Citing 1
Cited 4

On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence

A Low Cost Incremental Biometric Fusion Strategy for a Handheld Device

SSPR & SPR '08 Proceedings of the 2008 Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
A study on enhanced dynamic signature verification for the embedded system

BVAI'05 Proceedings of the First international conference on Brain, Vision, and Artificial Intelligence
A user-specific and selective multimodal biometric fusion strategy by ranking subjects

Pattern Recognition
A survey of multiple classifier systems as hybrid systems

Information Fusion

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper we propose a multi-expert architecture, particularly suited for verification systems, which attempts to offer the performance advantages of a serial approach while retaining the reliability of a parallel combination scheme. In this framework, criteria for evaluating the reliability of both the intermediate answers and the final response are provided, together with a method for the determination of an optimal reject option. This architecture has been tested on a signature verification application, confirming the effectiveness of the proposed approach.