A method to make multiple hypotheses with high cumulative recognition rate using SVMs.

DOI10.1016/S0031-3203(03)00236-XzbMath1059.68092OpenAlexW1991405589MaRDI QIDQ1425940

Hidetoshi Miyao, Yasuaki Nakano, Minoru Maruyama, Ken-ichi Maruyama

Publication date: 14 March 2004

Published in: Pattern Recognition (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0031-3203(03)00236-x

zbMATH Keywords

Support vector machinesHybrid methodDAGSVMJEITA-HPMax-Win algorithmRank information

Mathematics Subject Classification ID

Nonnumerical algorithms (68W05) Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Related Items (2)

A novel and quick SVM-based multi-class classifier ⋮ Choosing the kernel parameters for support vector machines by the inter-cluster distance in the feature space

Uses Software

• SVMlight

Cites Work

• Handwritten digit recognition: Benchmarking of state-of-the-art techniques.
• Support-vector networks
• Choosing multiple parameters for support vector machines
• Unnamed Item

This page was built for publication: A method to make multiple hypotheses with high cumulative recognition rate using SVMs.