Multiple reject thresholds for improving classification reliability

DOI10.1007/3-540-44522-6_89MaRDI QIDQ4536580zbMATH OpenFDO

Authors Giorgio Fumera, Fabio Roli, Giorgio Giacinto

Publication date 5 November 2002

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/3-540-44522-6_89

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99)

Recommendations

• Error rejection in linearly combined multiple classifiers
• scientific article; zbMATH DE number 1123573
• An optimal reject rule for binary classifiers
• The Nearest Neighbor Classification Rule with a Reject Option
• scientific article; zbMATH DE number 2013261

Cites work

• Multiple reject thresholds for improving classification reliability
• On optimum recognition error and reject tradeoff

Cited in

(7)

• Consistent algorithms for multiclass classification with an abstain option
• Weightless neural networks for open set recognition
• Learning with Rejection
• Multiple reject thresholds for improving classification reliability
• Classification with reject option
• A consistent statistical test based on bivariate random samples
• Predictor-rejector multi-class abstention: theoretical analysis and algorithms

This page was built for publication: Multiple reject thresholds for improving classification reliability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4536580)