Paravision brings face biometrics to the network edge with Ambarella CVflow platform support

Paravision has launched an AI toolset to provide full support for Amberella’s CVflow AI vision processing architecture, enabling its face biometrics to be built into transformative solutions for enterprise access control, video security, payments, home automation, and IoT applications, according to a company announcement.

The support for CVflow allows Paravision’s facial recognition algorithms and other AI computer vision capabilities to be implemented at the network edge to eliminate latency, reduce bandwidth requirements, and improve biometric privacy protection while maintaining accuracy and processing speed, the company says. Paravision states in the press release that its technology can be deployed to ultra-compact, fanless IoT devices while delivering a face detection and image quality assessment at greater than 30 fps, and one-to-many identification in less than 100 milliseconds.

“We’re truly excited to start a new chapter in Edge AI with support of Ambarella’s CVflow architecture,” says Paravision Chief Product Officer Joey Pritikin. “Through this deep integration, we have the opportunity to enable new paradigms for user experience and industrial design, bandwidth efficiency, and biometric privacy.”

The announcement says Ambarella’s combination of best-in-breed image signal processing, neural network acceleration, and power efficiency make it the platform of choice for computer vision at the edge. CVflow system-on-chips include the CV2, CV22, and CV25.

“The combination of Paravision software stack and Ambarella’s CVflow offers solution providers a truly compelling path to deliver face recognition and associated computer vision to a broad range of IoT applications,” comments Chris Day, vice president of marketing and business development for Ambarella. “This is a powerful pairing for partners looking for trusted, high-performance AI-powered computer vision at the edge.”

Article Topics

AI  |  Ambarella  |  biometric identification  |  biometrics  |  biometrics at the edge  |  face detection  |  facial recognition  |  IoT  |  Paravision  |  research and development