2003 · 92 citations · 5 references
ComputingBioengineeringComputer VisionFeature EngineeringSensor FusionBiometric AuthenticationBiometricsEnsemble MethodsFace RecognitionMultimodal AnalysisMultimodal InteractionBiometric FusionBiometric System Performance EvaluationClassifier FusionConfidence LevelMultimodal AuthenticationMultimodal Biometric AuthenticationMultimodal Classification FusionNormalization
Multimodal biometric systems outperform single-mode systems in small-scale populations, as shown by experimental studies. The study investigates whether multimodal biometric techniques scale to larger populations, introduces a performance-testing methodology, and evaluates the feasibility of using COTS products for deployable systems. The methodology leverages confidence scores from existing single-mode data, applies normalization and fusion techniques to face and fingerprint classifiers, and evaluates the system on a 1,000-subject population—ten times larger than prior studies. Combining face and fingerprint classifiers yields significant performance gains over single-mode biometric systems.
Experimental studies show that multimodal biometric systems for small-scale populations perform better than single-mode biometric systems. We examine if such techniques scale to larger populations, introduce a methodology to test the performance of such systems, and assess the feasibility of using commercial off-the-shelf (COTS) products to construct deployable multimodal biometric systems. A key aspect of our approach is to leverage confidence level scores from preexisting single-mode data. An example presents a multimodal biometrics system analysis that explores various normalization and fusion techniques for face and fingerprint classifiers. This multimodal analysis uses a population of about 1000 subjects, a number ten-times larger than seen in any previously reported study. Experimental results combining face and fingerprint biometric classifiers reveal significant performance improvement over single-mode biometric systems.
5
Josef Kittler, M. Hatef, Robert P. W. Duin et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 1998 · 5.3K citations