International Conference on Artificial Intelligence · 2004 · 15 citations · 10 references
ComputingComputer ScienceAuthenticationComputer VisionDiscriminationBiometric AuthenticationBiometricsDigital AuthenticationFace RecognitionOptical Character RecognitionPattern RecognitionBiometric Feature ExtractionBiometric RecognitionBiometric System Performance EvaluationDiscrete Wavelet TransformHistogram MatchingIris RecognitionIris Recognition AuthenticationWavelet Transform
Quantitatively establishing the discriminative power of iris biometric data is considered. Multi-level 2D wavelet transform has been widely used for iris verification system. While previous approaches compute only means and variances, we propose using a histogram distance. We also use a methodology to establish a measure of discrimination that is statistically inferable. To establish the inherent distinctness of the classes, i.e., validate individuality, we transform the many class problem into a dichotomy by using a “distance” between two samples of the same person and between those of two different peoples. We demonstrate that using histogram matching results better performances than using only means and variances.
10
SN Srihari, Hitesh Arora, Soojin Lee · Journal of Forensic Sciences · 2002 · 517 citations
Computing, Psychology, Data Mining +16