Lithuanian tech firm Neurotechnology has today announced the release of VeriLook, a new algorithm used for face recognition. The company, which creates technologies for high-precision biometric identification, has created VeriLook as part of its new MegaMatcher 9.0 line of biometric software development kits, which also includes fingerprint, face, iris, palmprint and voice identification technologies.
Based on deep neural networks, VeriLook provides five times higher accuracy in full frontal face recognition and a 10 to 15-fold accuracy increase in unconstrained facial recognition compared to previous models. The product also features a simpler, more intuitive interface for easy integration and use in authentication tasks such as user verification for mobile banking transactions. It can also be used in combination with other MegaMatcher 9.0 products for multi-biometric solutions.
According to Dr. Justas Kranauskas, project lead for Neurotechnology , VeriLook will greatly simplify verification tasks such as user authentication. “With this new version our development team focused on face recognition in real-world, unconstrained environments,” Dr. Kranauskas explains. “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,” he added.
This improved facial recognition algorithm both reduces errors and makes the product significantly easier to use, enabling it to be applied to a much broader range of face recognition applications. These include conducting automated facial image searches on large databases without the need for manual review. It is also more accurate at detecting a range of attributes such as gender, and can manage images with more complex facial poses. And its optional liveness detection enables it to determine if the system is viewing a live person or a photograph, a key quality for user authentication. Additional updates to the MegaMatcher 9.0 line include an enhanced iris algorithm that improves extraction speed and iris segmentation quality.
Vilnius-based Neurotechnology, which was founded in 1990, has distributors worldwide. VeriLook algorithms have been deployed more than one million times worldwide over the past 12 years, with the latest version set to be popular across the globe.
Thanks for reaching out to us, this means a lot! We will get back to you shortly.
Meanwhile, we invite you to discover what’s new in the Lithuanian business landscape.