Role of statistical dependence between classifier scores in determining the best decision fusion rule for improved biometric verification

Authors:
Krithika Venkataramani;B. V. K. Vijaya Kumar
Affiliations:
ECE Department, CyLab, Carnegie Mellon, Pittsburgh, PA;ECE Department, CyLab, Carnegie Mellon, Pittsburgh, PA
Venue:
MRCS'06 Proceedings of the 2006 international conference on Multimedia Content Representation, Classification and Security
Year:
2006

Citing 5
Cited 1

Ensemble learning via negative correlation

Neural Networks
Distributed Detection and Data Fusion

Distributed Detection and Data Fusion
Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy

Machine Learning
Real-Time Face Recognition Using Gram-Schmidt Orthogonalization for LDA

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Conditionally dependent classifier fusion using AND rule for improved biometric verification

ICAPR'05 Proceedings of the Third international conference on Pattern Recognition and Image Analysis - Volume Part II

Iterative Boolean combination of classifiers in the ROC space: An application to anomaly detection with HMMs

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Statistical dependence between classifier scores has been shown to affect the verification accuracy for certain decision fusion rules (e.g.,‘majority', ‘and', ‘or'). In this paper, we investigate what are the best decision fusion rules for various statistical dependences between classifiers and check whether the best accuracy depends on the statistical dependence. This is done by evaluating accuracy of decision fusion rules on three jointly Gaussian scores with various covariances. It is found that the best decision fusion rule for any given statistical dependence is one of the three major rules – ‘majority',‘and', ‘or'. The correlation coefficient between the classifier scores can be used to predict the best decision fusion rule, as well as for evaluation of how well-designed the classifiers are. This can be applied to biometric verification; and it is shown using the NIST 24 fingerprint database and the AR face database that the prediction and evaluation agree.