Modified product fusion

Pattern Recognition Letters

Volumn 23, Issue 8, 2002, Pages 957-965

  Alkoot, F M ^a   Kittler, J ^a  

^a UNIVERSITY OF SURREY   (United Kingdom)

Author keywords

Classifier combination; Estimation accuracy; Posterior probability; Product fusion strategy; Veto

Indexed keywords

PARAMETER ESTIMATION;

OPTIMAL OPERATING POINT;

PATTERN RECOGNITION;

PATTERN RECOGNITION;

EID: 0036605017     PISSN: 01678655     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-8655(02)00025-9     Document Type: Article

References (16)

1. Experimental evaluation of expert fusion strategies
2. Population bias control for bagging knn experts
3. Bagging predictors
4. Solving multiclass learning problems via error-correcting output codes
5. Generalised approach to the recognition of structurally similar handwritten characters using multiple expert classifiers
6. Experiments with a new boosting algorithm
7. Decision combination in multiple classifier systems
8. Methods for combining experts' probability assessments
9. Hierarchical mixture of experts and the em algorithm
10. Combining classifiers: A theoretical framework
11. On combining classifiers
12. Combining multiple classifiers by averaging or by multiplying
13. Stacked generalisation
14. Combination of multiple experts using local accuracy estimates
15. Methods of combining multiple classifiers and their applications to handwriting recognition