Jain and students licensed technology

Latent fingerprint recognition continues to be one of the most challenging problems in fingerprint recognition which is used to establish the identity of a suspect associated with partial and smudgy fingerprints, called latent prints or fingermarks,  left at a crime scene. MSU algorithm is based on a deep network model that combines global embeddings with local embeddings, achieving state-of-the-art latent to rolled matching accuracy with high throughput. Thales, one of the top-3 performers in NIST Fingerprint Vendor Technology Evaluation (FpVTE), licensed the technology after a detailed evaluation of MSU algorithms on benchmark datasets and comparison against its own solution. Details of the algorithm are available in the following publication.

Steven Grosz and A. K. Jain, "Latent Fingerprint Recognition: Fusion of Local and Global Embeddings", IEEE Transactions on Information Forensics and Security, vol. 18, pp. 5691-5705, 2023, doi: 10.1109/TIFS.2023.3314207. Provisional patent filed.

In addition to this technology transfer, Jain's lab has licensed three additional technologies in the past 3 years, all to NEC North America. These technologies deal with learning a fixed-length fingerprint embedding and algorithms for computer-generated fingerprint images for data augmentation. NEC America is also one of the top three global vendors in both fingerprint and face recognition technology evaluations conducted by NIST. These three algorithms are described in the following papers.

A. B. V. Wyzykowski and A. K. Jain, "Synthetic Latent Fingerprint Generator", IEEE Workshop on Applications of Computer Vision, Kona, HI, Jan 3-7, 2023.

J. J. Engelsma, S. A. Grosz and A. K. Jain, "PrintsGAN: Synthetic Fingerprint Generator", IEEE Trans. on Pattern Analysis and Machine Intelligence, DOI: 10.1109/TPAMI.2022.3204591, 2022.

J. J. Engelsma, K. Cao and A. K. Jain, "Learning a Fixed-Length Fingerprint Representation", IEEE Trans. on Pattern Analysis and Machine Intelligence, DOI 10.1109/TPAMI.2019.2961349, 2019. US Patent No. 11,373,438 B2, June 28, 2022.

MSU Technologies (MSUT) generated a total income of approximately 1 million from these 4 licenses.

(Date Posted: 2023-11-15)