Tech

Neurotechnology Advances With New Face Algorithm

By Ashley McGuire , Jun 03, 2016 08:00 AM EDT
Close

Neurotechnology is a provider of high-quality biometric identification technologies of today's generation. It has currently released the so-called VeriLook, which is a face recognition algorithm.

According to Canada Journal, VeriLook is introduced with "a new face verification component" with a more intuitive but simpler interface that is easily integrated and used for authentication tasks like mobile banking transaction verifications.

It is said that with its new algorithm, it has five times higher accuracy in the identification of full frontal faces. Also, it has 10 to 15 times higher accuracy in unrestricted facial recognition.

Dr. Justas Kranauskas, Neurotechnology's project leader, said "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."

Moreover, as reported by Biometric, the advancement of the face recognition algorithm makes it importantly easier to utilize and apply to a more broader range of facial recognition applications, i.e., automated facial image searches in huge databases. By this, it would not need manual review. Besides, it would be able to detect faces accurately in a much faster way.

It is further reported that VeriLook is a part of the new MegaMatcher 9.0 line of biometric software development kits (SDK). Also released along with it are fingerprint, iris, palmprint, face and voiceprint (speaker) identification technologies that could work seamlessly together and can be utilized in any combination for multi-biometric solutions.

In addition, the improvements also span the easy detection of facial attributes that include smile, gender, open mouth, closed eyes, dark glasses and eyeglasses. This new facial landmarks tracking and detection capabilities are more well made in a wider range of facial poses.

Non-compulsory liveness detection determines if the algorithm is looking at a live person or 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," as further noted by Biometric.

© 2019 ITECHPOST, All rights reserved. Do not reproduce without permission.
Real Time Analytics