Publication Details
Bimodal Eye Imaging System for Biometric and Medical Applications
Semerád Lukáš, Ing., Ph.D. (DITS)
Drahanský Martin, prof. Ing., Ph.D.
Odstrčilík Jan, Ing., Ph.D. (UBMI)
Hájek Josef, Ing., Ph.D.
Borovský Ján, Ing.
eye imaging, iris, retina, biometrics, humanrecognition, security
The proposedcontribution presents a new bimodal imaging system for simultaneous acquisitionof the human iris and retina. The system is intended to use in high securityapplications for biometric human recognition (high-secured access) as well asin medical applications for possible use in ophthalmology. Biometricidentification systems have become a common part of security applications. Irisor retina recognition is not a new idea, but if we consider these two as amultimodal system, it gives us a totally different view to the security andreliability of a respective biometric system. Common biometric systems inreal-world applications are usually unimodal and thus can handle only onesingle biometric source of information (i.e. biometric characteristic) -usually a pattern of the human eye iris. Due to the fine and unique texture ofiris, the probability of having the same iris texture is around 1 in 1078[1], which ensures sufficient coverage of population. However, the fact theiris is located visibly on anterior segment of the eye and thus it is possibleto take an iris photo from a distance of some meters, the risk of the irispattern will be copied and subsequently counterfeited is relatively high. Onthe other side, the retina recognition is not currently used in practice atall. This is caused by several factors, e.g. complicated optical system, price,and low user-friendliness. Retinal recognition has clear advantages inuniqueness, number of features compared to other biometrics, and also that itis the only place in the human body with the possibility to observe the bloodvessels non-invasively [2]. Hence, the retinal images can be utilized not onlyfor biometrics, but also for medical purposes as a source of information fordiagnosis, e.g. of various cardiovascular diseases, glaucoma, maculardegeneration, diabetic retinopathy, and other disease that can be detected fromretinal images. Unimodal biometric systems are generally susceptible to varietyof issues such as intra-class variations, inter-class similarities, noisy data,non-universality, and spoofing. Hence, by combining iris and retina into oneunique solution, it is possible to get very robust biometric recognition device.The proposed bimodal imaging system is designed as a part of the researchproject at the Brno University of Technology. The device allows simultaneousacquisition of iris and retina. Integrated illumination sources operate at bothvisible and near-infrared light. The whole optical system is mounted on an adjustable3D platform which is controlled by a feedback from acquired images. Thanks to the 3D movable platform, we assume that the proposedbiometric system will be more user friendly and in addition, the time ofscanning will be much less than in case of other systems
@inproceedings{BUT119840,
author="Radim {Kolář} and Lukáš {Semerád} and Martin {Drahanský} and Jan {Odstrčilík} and Josef {Hájek} and Ján {Borovský}",
title="Bimodal Eye Imaging System for Biometric and Medical Applications",
booktitle="Security and Protection of Information 2015",
year="2015",
pages="83--95",
publisher="University of Defence in Brno",
address="Brno",
isbn="978-80-7231-997-8"
}