Virtual environment for 3-D synthetic fingerprints

Contactless biometric recognition performed using three-dimensional fingerprint models has the advantages of reducing problems related to the deformations of the skin, dust on the sensor, and spoofing of latent fingerprints. Moreover, the fingerprint area usable for the recognition is wider than the one captured by traditional contact-based acquisition techniques. The design of fingerprint recognition systems based on three-dimensional models, however, requires the collection of large datasets of samples. This task is expensive and time consuming, and can also require the implementation of new hardware setups. For this reason, the use of virtual environments for the generation of realistic synthetic models can be useful for the evaluation of new biometric algorithms. In the literature, there are methods for the computation of synthetic fingerprint models that resemble fingerprint images acquired using a touch-based sensor. However, at the best of our knowledge, there are no works dealing with the computation of synthetic three-dimensional models of fingerprints. In this paper, we propose a virtual environment able to compute synthetic three-dimensional fingerprints, which can be useful for the entire research community working in the fields of biometrics and three-dimensional reconstruction. The method is based on image processing techniques and algorithms designed for fingerprint recognition applications. The method is validated by comparing the results obtained with contactless fingerprint acquisitions. Results show that the method is feasible and produces three-dimensional models that are realistic and visually comparable with real fingerprints.