2026-05-21
Kneron’s 3D Facial Recognition Module for Secure Edge AI Access Control
Kneron, a global leader in edge AI computing solutions, announced its latest 3D Binocular Facial Recognition Module, integrating proprietary edge AI chips, lighting AI algorithmsand infrared liveness detection technologies to deliver highly secure, low-power facial authentication for smart access control applications.
Designed for smart homes, enterprise security, and smart city deployments, the solution combines stereo vision cameras with Near-Infrared (NIR) imaging to generate accurate 3D facial depth information while detecting real human skin characteristics. The system effectively defends against spoofing attacks using photos, replay videos, and high-precision 3D masks, and has passed payment-grade verification as well as ISO 30107 and ISO 19795 anti-spoofing certification tests.
The module is powered by Kneron’s KL520 edge AI architecture featuring a reconfigurable Neural Processing Unit (NPU) optimized for high AI inference efficiency and ultra-low power consumption. Compared with competing solutions, the lightweight AI model architecture achieves over 2x higher energy efficiency (FPS/W).
Using multi-model AI framework integrates facial recognition, liveness detection, facial occlusion analysis, and head pose estimation into a compact edge AI solution. Through model optimization and lightweight attention mechanisms, the company reduced model latency by 46%, lowered parameter size by 25%, and improved inference performance by approximately 39%.
Optimized for battery-powered devices, the module supports up to 350 days of operation using AA batteries and approximately six months with lithium-ion battery configurations, making it ideal for smart locks and always-on edge security systems.
Kneron stated that it will continue expanding its edge AI and intelligent sensing portfolio to accelerate deployment of secure, energy-efficient AI authentication technologies across global smart security and intelligent infrastructure markets.
Designed for smart homes, enterprise security, and smart city deployments, the solution combines stereo vision cameras with Near-Infrared (NIR) imaging to generate accurate 3D facial depth information while detecting real human skin characteristics. The system effectively defends against spoofing attacks using photos, replay videos, and high-precision 3D masks, and has passed payment-grade verification as well as ISO 30107 and ISO 19795 anti-spoofing certification tests.The module is powered by Kneron’s KL520 edge AI architecture featuring a reconfigurable Neural Processing Unit (NPU) optimized for high AI inference efficiency and ultra-low power consumption. Compared with competing solutions, the lightweight AI model architecture achieves over 2x higher energy efficiency (FPS/W).
Using multi-model AI framework integrates facial recognition, liveness detection, facial occlusion analysis, and head pose estimation into a compact edge AI solution. Through model optimization and lightweight attention mechanisms, the company reduced model latency by 46%, lowered parameter size by 25%, and improved inference performance by approximately 39%.
Optimized for battery-powered devices, the module supports up to 350 days of operation using AA batteries and approximately six months with lithium-ion battery configurations, making it ideal for smart locks and always-on edge security systems.
Kneron stated that it will continue expanding its edge AI and intelligent sensing portfolio to accelerate deployment of secure, energy-efficient AI authentication technologies across global smart security and intelligent infrastructure markets.
