Data-driven Reconstruction of Fingerprints from Minutiae Maps

In this paper we explore the power of conditional generative adversarial networks and in particular of the pix2pix network to reconstruct realistic fingerprint patterns from minutiae maps. In our considerations a minutiae map is a grayscale image that encodes minutiae locations and orientations as these are presented in a minutiae template. We propose a novel approach for minutiae encoding in a minutiae map and study to which degree the reconstruction may be successful if trained with a low number of samples. Moreover, we explore the generalization ability of the trained models in cross-dataset and cross-sensor experiments. Reconstruction from pseudo-random minutiae enables synthesis of anonymous fingerprints as well as controlling the diversity of generated samples including synthesis of mated fingerprints which is vital for compilation of large-scale public evaluation datasets.