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
- Look Twice as Much as You Say: Scene Graph Contrastive Learning for Self-Supervised Image Caption Generation
- Visualization of partial bloody fingerprints on nonporous substrates using columnar thin films
- Quantifying the strength of palmprint comparisons: Majority identifications with surprisingly low value