Number of the records: 1
Information analysis of multiple classifier fusion
- 1.
SYSNO ASEP 0410599 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Information analysis of multiple classifier fusion Author(s) Grim, Jiří (UTIA-B) RID, ORCID
Kittler, J. (GB)
Pudil, Pavel (UTIA-B) RID
Somol, Petr (UTIA-B) RIDIssue data Berlin: Springer, 2001 ISBN 3-540-42284-6 Source Title Multiple Classifier Systems / Kittler J. ; Roli F. Pages s. 168-177 Series Lecture Notes in Computer Science. Series number 2096 Number of pages 10 s. Action Multiple Classifier Systems. MCS 2001 Event date 02.07.2001-04.07.2001 VEvent location Cambridge Country GB - United Kingdom Event type WRD Language eng - English Country DE - Germany Keywords pattern recognition ; finite mixtures ; multiple solutions Subject RIV BB - Applied Statistics, Operational Research R&D Projects GA402/01/0981 GA ČR - Czech Science Foundation (CSF) KSK1019101 GA AV ČR - Academy of Sciences of the Czech Republic (AV ČR) CEZ 1075907 Annotation We consider a general scheme of parallel classifier combinations in the framework of statistical pattern recognition. Each statistical classifier defines a set of output variables in terms of a posteriori probabilities, i.e. it is used as a feature extractor. The output vectors of classifiers are combined in parallel. The statistical Shannon information is used as a criterion to compare different combining schemes. By means of relatively simple arguments we derive a hierarchy between different methods. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201.
Number of the records: 1