Theoretical and Experimental Determination of the Amount of Information in Human Ocular Biometric Characteristics
The aim of this work is to design method and quantify amount of biometric entropy in the human retina. In other words, this work seeks to determine how unique this biometric feature is, and whether universality is ensured in the human population. The first part shows how the human eye works, especially with regard to the retina. Is also mentioned the physiological basis of angiogenesis in the retina, on which biometric recognition is based in the work's next part. Further are noted ophthalmological devices designed by the STRaDe research group, which are equipped algorithms for detection of the most common diseases in the retina, which are manifested by a visual change. The fourth part presents a tool for generating synthetic retinas, which can be used to create databases for testing other algorithms. Further part deals with the statistical evaluation of the points and properties of the retina, from which it's based the theoretical formula for the calculation retina biometric entropy. In the final chapter are outlined several principles for quantify the mentioned theoretical formula. The work could serve to prove the uniqueness of biometric devices based on retinal scanning, which are currently not very widespread.
Human eye, retina, biometrics, biometric entropy, biometric system, vessel bifurcation, vessel crossing, retina diseases, synthetic retina images, retina statistical properties.