Entropy estimator and formal model for vascular skeletons

Abstract

Currently biometric systems are evaluated using performance measures like the Equal Error Rate in database comparisons. The biometric performance can give an indication how good a certain system is suited to handle the biometric samples. However, there are more factors of reasoning: test data and simulations are always limited and the performance does not give any insight in how discriminating the features from a certain source are in theory. In this paper we propose a model for vein skeletons and an entropy estimator on the skeletonized representation of the vein patterns to overcome the before mentioned limitations. The results are compared to information theoretical entropy estimations on a specific finger vein database.