PrintsGAN: Synthetic Fingerprint Generator
This addresses a data scarcity problem for fingerprint recognition researchers, enabling improved model training with synthetic data, though it is incremental in enhancing existing methods.
The authors tackled the lack of large-scale public fingerprint datasets by proposing PrintsGAN, a synthetic fingerprint generator that created a database of 525k fingerprints (35K distinct fingers, each with 15 impressions). They demonstrated its utility by training a deep network on synthetic data and fine-tuning on real fingerprints, achieving a TAR of 87.03% @ FAR=0.01% on NIST SD4, a boost from 73.37%.
A major impediment to researchers working in the area of fingerprint recognition is the lack of publicly available, large-scale, fingerprint datasets. The publicly available datasets that do exist contain very few identities and impressions per finger. This limits research on a number of topics, including e.g., using deep networks to learn fixed length fingerprint embeddings. Therefore, we propose PrintsGAN, a synthetic fingerprint generator capable of generating unique fingerprints along with multiple impressions for a given fingerprint. Using PrintsGAN, we synthesize a database of 525k fingerprints (35K distinct fingers, each with 15 impressions). Next, we show the utility of the PrintsGAN generated dataset by training a deep network to extract a fixed-length embedding from a fingerprint. In particular, an embedding model trained on our synthetic fingerprints and fine-tuned on a small number of publicly available real fingerprints (25K prints from NIST SD302) obtains a TAR of 87.03% @ FAR=0.01% on the NIST SD4 database (a boost from TAR=73.37% when only trained on NIST SD302). Prevailing synthetic fingerprint generation methods do not enable such performance gains due to i) lack of realism or ii) inability to generate multiple impressions per finger. We plan to release our database of synthetic fingerprints to the public.