TECH5, an innovator in the field of biometrics and digital identity management, receives a patent (United States Patent 11721120) for “Contactless fingerprint capture using artificial intelligence and image processing on integrated camera systems”. With this patent, the company is aiming to protect one of its latest innovations – a neural network (NN) based mobile fingerprint liveness and capture technology called T5-AirSnap Finger.
The patent covers a fingerprinting solution that uses neural network (NN) based Machine Learning (ML) algorithms in combination with traditional image processing for contactless fingerprint capture, presentation attack detection, and fingerprint matching using a portable handheld device with integrated camera systems, thereby eliminating the need for a specialist device dedicated for fingerprinting. NN models are trained to first detect the size and direction of fingers in the captured image, check if the captured fingers are reversed (thereby making nails visible), check if the thumb of the correct hand is captured, check if the presented finger is live or a spoof, and generate fixed-length fingerprint templates for subsequent matching of fingerprints. A three-dimensional (3D) depth map of the finger is used to bring the fingerprint resolution to 500 dpi and eliminate distortion caused by the curvature of the finger shape to improve accuracy while scaling and flattening a fingerprint image. The solution facilitates contactless-to-contactless as well as contactless-to-contact-based fingerprint matching.
T5-AirSnap Finger efficiently captures and prepares biometric data for further processing in compliance with interoperability standards. The algorithms can be used for both enrolment and authentication on a mobile device and backend.
TECH5 has been participating with its contactless fingerprint capture technology in the UK Home Office Biometric self-enrolment trials consistently since 2021. Furthermore, TECH5’s fingerprint capture and matching technologies are part of ongoing evaluations by NIST (National Institute of Standards and Technology) and the FBI as part of the standardisation and certification of such technologies.
In June 2023, TECH5 won the first and second positions in the Liveness Detection (LivDet)1 2023 Non-contact Fingerprint international competition, with its latest NN (neural network) based fingerprint liveness detection technology for mobile devices. This technology is available to TECH5’s certified partners globally as part of T5-AirSnap Finger contactless capture offering for mobile devices.
“TECH5 is passionate about driving innovation and revolutionising the way we solve real-world problems. Our expert R&D team is committed to advancing contactless fingerprint capture and liveness detection, integral to critical applications such as national enrolments, law enforcement, eKYC, and decentralised digital ID. We take pride in leading the way in this exciting new field of research.” – says Rahul Parthe, TECH5’s Co-founder, Chairman, and CTO, listed in the patent among inventors.
T5-AirSnap Finger technology is deployed in various projects across Government and Private sectors as part of the T5-Digital ID solution as well as a separate product.