Fingerprint Synthesis Via Latent Space Representation

Abstract

Fingerprint recognition and indexing were addressed extensively in the literature. However, the number of the datasets that are used for research and validation is limited. Due to privacy laws and acts in several countries, it is challenging to release finger prints to the public. Consequently, this imposes a challenge on validating these search techniques on larger datasets that can be couple of hundreds of millions. To overcome this limitation, synthetic fingerprints datasets have been introduced as an alternative solution. In this paper we propose a generative model for synthesising fingerprint datasets. In this present work, the synthetic fingerprints are generated from the latent space representation using variational auto encoder. The network is trained to generate random samples that have same distribution as real finger print using latent vectors. By examining the generated synthetic fingerprints images, the ridge patterns were recognisable in most of cases. The unrecognisable synthetic images are reflecting the presence of low quality images in the training samples of the original dataset. Moreover, the extraction of minutiae relies on the quality of the input fingerprint images. In conclusion, the proposed method was able to generate synthetic image that can be further processed to accurately extract the finger minutiae and orientation field.