Robust fusion: extreme value theory for recognition score normalization

Authors:
Walter Scheirer;Anderson Rocha;Ross Micheals;Terrance Boult
Affiliations:
University of Colorado at Colorado Springs & Securics, Inc.;Institute of Computing, University of Campinas;National Institute of Standards and Technology;University of Colorado at Colorado Springs & Securics, Inc.
Venue:
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Year:
2010

Citing 12
Cited 4

A compact and efficient image retrieval approach based on border/interior pixel classification

Proceedings of the eleventh international conference on Information and knowledge management
Face Recognition from Long-Term Observations

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Modeling and Predicting Face Recognition System Performance Based on Analysis of Similarity Scores

IEEE Transactions on Pattern Analysis and Machine Intelligence
Image retrieval: Ideas, influences, and trends of the new age

ACM Computing Surveys (CSUR)
Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
A multimodal biometric test bed for quality-dependent, cost-sensitive and client-specific score-level fusion algorithms

Pattern Recognition
Benchmarking quality-dependent and cost-sensitive score-level multimodal biometric fusion algorithms

IEEE Transactions on Information Forensics and Security - Special issue on electronic voting
Adaptive threshold estimation via extreme value theory

IEEE Transactions on Signal Processing
Score normalization in multimodal biometric systems

Pattern Recognition
Models of large population recognition performance

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
How do correlation and variance of base-experts affect fusion in biometric authentication tasks?

IEEE Transactions on Signal Processing
Incorporating Model-Specific Score Distribution in Speaker Verification Systems

IEEE Transactions on Audio, Speech, and Language Processing

Reduced analytical dependency modeling for classifier fusion

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Computer generated images vs. digital photographs: A synergetic feature and classifier combination approach

Journal of Visual Communication and Image Representation
Visual words dictionaries and fusion techniques for searching people through textual and visual attributes

Pattern Recognition Letters
Multimedia event detection with multimodal feature fusion and temporal concept localization

Machine Vision and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recognition problems in computer vision often benefit from a fusion of different algorithms and/or sensors, with score level fusion being among the most widely used fusion approaches. Choosing an appropriate score normalization technique before fusion is a fundamentally difficult problem because of the disparate nature of the underlying distributions of scores for different sources of data. Further complications are introduced when one or more fusion inputs outright fail or have adversarial inputs, which we find in the fields of biometrics and forgery detection. Ideally a score normalization should be robust to model assumptions, modeling errors, and parameter estimation errors, as well as robust to algorithm failure. In this paper, we introduce the w-score, a new technique for robust recognition score normalization. We do not assume a match or non-match distribution, but instead suggest that the top scores of a recognition system's non-match scores follow the statistical Extreme Value Theory, and show how to use that to provide consistent robust normalization with a strong statistical basis.