Offline High Security AI Binocular 3D Vision Recognition Sensor for Face Vein QR Code Detection Scanning Home

Offline High Security AI Binocular 3D Vision Recognition Sensor for Face Vein QR Code Detection Scanning Home Kuvaus

home systems integration for enhanced security and convenience.
Dual 1/5" CMOS cameras with 2MP resolution for high-quality video capture.
Advanced algorithms including deep learning face recognition and vein recognition.
Binocular liveness detection with a low false acceptance rate (FAR 1%).
User capacity of 1,000 faces and 1,000 veins, with multi-angle enrollment support and a detection range of 30-120 cm for faces.

Applications
home systems
door locks
Self-service retail payment terminals

Hardware Parameters
SoC: Arm CPU@900MHz, [email protected], RISC-V@600MHz
DDR2: 64MB
Flash: 32MB
Cameras: Dual 1/5" CMOS, 2MP, dual MIPI interfaces
Lens: FOV: 83 diagonal; optimal focus: 60cm
LED: IR@850nm, RGB@650nm (90 illumination)
USB: UVC video transmission (expandable to UAC); MJPEG output (H.264/YUY2 expandable)
Communication: UART@115200 baud

Power Parameters
Supply voltage: 5-12V
Operating current: 320-330mA@8V
Standby current: 120-130mA (auto-detection mode)
Shutdown current: 0µA (non-auto-detection mode)

Other Parameters
Operating temperature: -20C to +60C
Storage temperature: -30C to +70C
Humidity: 10-93% RH (non-condensing)
Audio I/O: Expandable (speaker/microphone)
Boot : 900ms-2.5s (varies with stored user count)
Algorithms: Binocular liveness detection, deep learning face recognition, vein recognition, QR code recognition
Liveness metrics:
FAR (False Acceptance Rate) 1%
FRR (False Rejection Rate) 1%
Face recognition:
Pass rate: 98.85%
FAR: 0.001%
Recognition angle: 20 pitch/yaw; supports multi-angle enrollment
Detection range: Face: 30-120 cm, vein / QR code:15cm
Color: Black
Material: PCB

Pac