Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Most current ocular biometric systems are based on recognition and classification of unique iridial patterns typically captured in near infrared spectrum (NIR). However, eye images in the visible spectrum (e.g. RGB images) also reveal some iridial patterns in addition to the vascularity of the white of the eyes (mostly due to conjunctival and episcleral layers). These vascular patterns have rich and uniquely identifiable information. The combination of the aforementioned modalities provides an opportunity for bi-modal ocular biometrics using only visible spectrum captures. Multimodality improves the performance of biometric systems compared to single mode biometrics. In this work, a bi-modal ocular biometric system is described, where match scores from vasculature of the white of the eye and iris modalities are fused. We report the performance of this enhanced complementary biometric identification using UBIRIS v1 database. The proposed method, for a quality-vetted subset of UBIRIS v1 RGB ocular images, produces an area under receiver operating characteristic curve (AUC) of 0.9954 and an equal error rate (EER) of 0.0452. In comparison, individual modalities yield an AUC of 0.9822 and EER of 0.0759 for iris and an AUC of 0.9623 and an EER of 0.1022 for conjunctival vasculature. The proposed new algorithms may overcome constraints of using NIR imaging for iris and provide a better overall performance using only RGB eye images. We conclude that bi-modal iris–conjunctival fusion can improve the otherwise challenging RGB iris recognition.