This chapter presents a framework for multi-biometric match score fusion when non-ideal conditions cause conflict in the results of different unimodal biometrics classifiers.
The proposed framework uses belief function theory to effectively fuse the match scores and density estimation technique to compute the belief assignments. Fusion is performed using belief models such as Transferable Belief Model and Proportional Conflict Redistribution rule followed by the likelihood ratio-based decision making. Two case studies on multiclassifier face verification and multiclassifier fingerprint verification show that the proposed fusion framework with PCR5 rule yields the best verification accuracy even when individual biometric classifiers provide conflicting match scores (Published abstract provided)
Downloads
Similar Publications
- Principles of Fluorogenic Reagent Design for Forensics. Recent Progress Towards New Reagents to Develop Fingerprints in Blood and on Variable Surfaces
- Cellphone Contraband Detection Using Portable Ferromagnetic Detectors in a Correctional Environment
- An Examination of Charge Reduction and Conviction in Sexual Assault Cases: A Focal Concerns Analysis