Plurality voting-based multiple classifier systems: Statistically independent with respect to dependent classifier sets

Pattern Recognition

Volumn 35, Issue 11, 2002, Pages 2365-2379

  Demrekler, Mubeccel ^a   Altncay, Hakan ^b  

^a MIDDLE EAST TECHNICAL UNIVERSITY   (Turkey)

^b EASTERN MEDITERRANEAN UNIVERSITY   (Turkey)

Author keywords

Adding new classifiers; Bayesian formalism; Best distributions; Classifier selection; Independent distributions; Multiple classifier systems; Plurality voting; Statistical classifier combination; Statistical pattern recognition; Worst distributions

Indexed keywords

OPTIMIZATION;

MULTIPLE CLASSIFER SYSTEMS;

PATTERN RECOGNITION;

IMAGE CLASSIFICATION;

EID: 0036833267     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0031-3203(01)00227-8     Document Type: Article

References (20)

1. Decision combination in multiple classifier systems
2. On combining classifiers
3. A method of combining multiple probabilistic classifiers through soft competition on different feature sets
4. Unified decision combination framework
5. Information combination operators for data fusion: A comparative review with classification
6. Methods of combining experts' probability assessments
7. Optimal combinations of pattern classifiers
8. An information theoretic framework for weight estimation in the combination of probabilistic classifiers for speaker identification
9. Combination of multiple classifiers using local accuracy estimates
10. Combining the results of several neural network classifiers
11. Democracy in neural nets: Voting schemes for classification
12. Is independence good for combining classifiers
13. Neural network ensembles
14. Application of majority voting to pattern recognition: An analysis of its behavior and performance
15. Combination of weak classifiers
16. Building projectable classifiers of arbitrary complexity
17. On the algorithmic implementation of stochastic discrimination
18. The random subspace method for constructing decision forrests
19. A statistical unified framework for rank-based multiple classifier decision combination