New NXP developer tools enable machine learning biometrics on edge devices

NXP Semiconductors has launched an edge intelligence software environment for edge node developers to build machine learning applications in the cloud, along with turnkey solutions to make voice, vision, and anomaly detection application development accessible to customers without in-house ML expertise.

The NXP eIQ toolkit provides developers with tools to structure and optimize cloud-trained ML models to run efficiently in the resource-constrained IoT and other edge devices, and supports neural network frameworks such as TensorFlow Lite and Cafe2, as well as non-neural ML algorithms. The company has also expanded its EdgeScale software infrastructure for NXP devices with secure device onboarding, provisioning, and container management.

The turnkey solutions provide both the hardware and software to build applications, while allowing customers to add differentiation, and are modular, allowing, for example, voice recognition to be added to a product using NXP’s vision recognition solution, according to the announcement.

“Having long recognized that processing at the edge node is really the driver for customer adoption of machine learning, we created scalable ML solutions and eIQ tools, to make transferring artificial intelligence capabilities from the cloud-to-the-edge even more accessible and easy to use,” said Geoff Lees, senior vice president and general manager of microcontrollers for NXP.

NXP demonstrated some of the capabilities with a simulated factory floor using facial recognition for access by drone operators at last week’s IoT World Congress in Barcelona, and it will also demonstrate its latest edge computing technologies at ArmTechCom.

NXP also recently began collaborating with Precise Biometrics to produce contactless biometric smart cards.

Article Topics

biometrics  |  biometrics at the edge  |  cloud services  |  edge computing  |  machine learning  |  NXP Semiconductors