Latent Fingerprint Recognition using ISO 19794-2 Fingerprint Templates

Automated latent fingerprint recognition has gained a lot of attention from the law enforcement agencies to identify the suspects. Even though the fingerprint technology is more advanced, still there are many latent cases pending all over the world, due to lack of automated latent fingerprint recognition and also due to inadequate feature details because of smudged data and partial fingerprints. In this paper, a novel and automated latent fingerprint recognition algorithm is proposed in lights-out mode which is similar to normal plain fingerprint recognition algorithm. The algorithm uses the global and local adaptive binarization and global minutia features with ISO 19794-2 standard fingerprint templates. The efficacy of the proposed latent fingerprint algorithm is demonstrated on the standard NIST SD-27 (special database-27) latent fingerprint database.