Vascular biometrics based on a minutiae extraction approach

摘要

In this paper, the authors will describe a new algorithm based on minutiae extraction which is inspired by currently fingerprint systems, but adapted to the own characteristics of vein patterns. All the steps of the system, from the image pre-processing to the comparison algorithm, are described, including also the biometric feature extraction process. After describing the system, some obtained results are detailed. The algorithm proposed has been tested with two different databases: one database acquired by the authors, using a self-designed sensor; and one semi-publicly accessible database. These results do not only show the low error rates obtained but also the universality of the proposed system, as well as the ease of adapting the algorithm to cope with the different characteristics of each database