Neurotechnology, a provider of high-precision biometric identification technologies, today released the new VeriLook face recognition algorithm. Based on deep neural networks, the new algorithm provides five times higher accuracy in identifying full frontal faces and 10 to 15 times higher accuracy for unconstrained facial recognition.
With VeriLook, Neurotechnology also introduces a new face verification component with a simpler, more intuitive interface for easy integration and use in authentication tasks such as user verification for mobile banking transactions. VeriLook is included in the new MegaMatcher 9.0 line of biometric software development kits (SDK), also released today, which includes fingerprint, face, iris, palmprint and voiceprint (speaker) identification technologies that work seamlessly together and can be used in any combination for multi-biometric solutions.
“With this new version our development team focused on face recognition in real-world, unconstrained environments,” said Dr. Justas Kranauskas, project lead for Neurotechnology. “We achieved a ten-fold accuracy improvement on faces captured in lower resolution, with complex illumination, expressions and head rotations. This enabled us to offer a new face verification component which greatly simplifies user authentication by face, especially in mobile applications, while also enabling the face recognition algorithm to be used for complex 1:N identification,” Dr. Kranauskas added.
Improvements to the face recognition algorithm have resulted in much higher accuracy in facial identification compared to the previous version, based on False Rejection Rate (FRR) at the same False Acceptance Rate (FAR) value.
This not only improves the user experience by resulting in fewer errors, it makes the product significantly easier to use and apply to a much broader range of face recognition applications, such as conducting automated facial image searches in large databases without the need for manual review.
Faster face detection and more accurate estimation of facial attributes, including gender, smile, closed eyes, open mouth, glasses and dark glasses are also included. The new facial landmarks detection and tracking capabilities are more robust in a wider range of facial poses.
The new face verification component greatly simplifies both the technical and commercial use of facial recognition technology for user authentication purposes.
The easy-to-use, intuitive interface makes it highly suitable for use in mobile banking transactions and other applications which require both high security and simplicity. The component is optimized to make it easier to enroll and verify faces captured from cameras. Optional liveness detection determines if the system is viewing a live person vs. a photograph. A specialized API simplifies integration into a variety of solutions, and component pricing makes the face verification component economical for large-scale deployments on millions of devices.
Additional updates to the MegaMatcher 9 line include an enhanced iris algorithm that improves extraction speed and iris segmentation quality. It can accurately detect eyelids and can be used to locate irises in images that are captured in both the NIR range and in visible light. The iris image quality estimation is adapted to ISO/IEC 29794-6:2015 standard.