NXP launches microcontrollers for IoT edge face and voice biometrics
NXP Semiconductors has launched a pair of microcontroller (MCU)-based technologies to bring biometric facial and expression recognition, and far-field voice recognition capabilities to the edge on smart home, commercial, and industrial devices.
The new i.MX RT crossover MCU running FreeRTOS is used in both solutions, with facial recognition powered by the i.MX RT106F and voice recognition running on the i.MX RT106L, according to a pair of announcements. The turnkey solutions are intended to provide low latency and protect user privacy by avoiding the need for cloud connectivity.
The i.MX RT106F leverages NXP’s Oasis face processing engine with neural network capabilities for face detection, recognition, and anti-spoofing.
“Think about a toy that recognizes each member of the family and responds appropriately depending on their facial expressions or a smart appliance that can intuitively adjust its settings to a user’s preferences based on previous interaction,” says Denis Cabrol, executive director for NXP’s IoT Solutions. “All this is possible today with NXP’s turnkey, low cost solution. Developers are no longer constrained to Linux-based systems running on expensive multicore application processors that require large flash memory and SDRAM footprints, complex power management and costly, high layer count printed circuit boards.”
The i.MX RT106L offering provides integrated machine learning-based automatic commands recognition (ACR) technology for device command and control functions. In includes a wake word and four sets of example local commands out of the box, enabling developers to quickly create proof of concepts to add voice control tot heir products, the company says.
Both solutions are being demonstrated by the NXP at IFA in Berlin from September 6 to 11.
Goodix recently reached an agreement with NXP to acquire its voice and audio solutions business.