Offline AI Binocular 3D Vision Recognition Sensor (Face / Palm Vein / QR Code) - DFRobot

This AI binocular vision sensor is a self-contained multimodal recognition module designed for highly secure and versatile identity authentication. It works with a powerful integrated AI processor, using dual color and infrared cameras to perform all calculations locally. The heart of its functionality lies in its three-in-one identification capability, which integrates robust facial recognition, secure palm vein recognition, and universal QR code scanning into one compact device. Key features include advanced 3D viability detection for anti-spoofing, full offline AI processing that eliminates any computational load on the host system, and local storage for up to 1,000 users. With its simple UART interface, this offline AI vision sensor is ideal for rapid integration into applications such as secure access control, home automation systems, and automated retail terminals.

High-security biometrics with 3D vitality detection

Security is paramount in authentication systems. This facial recognition sensor uses a binocular (RGB + infrared) camera system to capture 3D depth information, enabling a sophisticated viability detection algorithm. This technology effectively distinguishes a live person from a 2D representation, providing robust protection against spoofing attempts using photos or videos. With a false acceptance rate (FAR) of facial recognition of 0.001%, the module provides an adequate level of security for critical access control applications.

Versatile 3-in-1 recognition functionality

The AI binocular vision sensor offers unparalleled flexibility by combining three distinct recognition methods. Facial recognition based on deep learning provides rapido contactless access. For added security, the vein and palm print recognition algorithm identifies unique subcutaneous venous patterns, a biometric marker that is extremely difficult to replicate. Finally, integrated QR code decoding offers a practical solution for granting temporary access, processing payments, or pairing devices, making the sensor adaptable to a wide range of operational requirements.

Powerful offline AI processing on module

Equipped with a dedicated System-on-Chip (SoC) with a 0.5 TOPS neural processing unit (NPU), the AI Vision camera handles all complex AI algorithms internally. This "edge computing" design means it requires no computing resources from the host device, enabling control from any microcontroller, including basic models such as Arduino Uno. All user data, including 1,000 face patterns and 1,000 palm vein patterns, are stored and processed locally, ensuring system performance, data privacy and functionality even without a network connection.

Seamless integration via UART and USB

Designed for easy implementation, the binocular camera communicates recognition results via a simple serial UART protocol, making integration into new and existing product designs simple. In addition, the USB interface supports the USB Video Class (UVC) protocol, enabling the module to transmit video like a standard webcam. This dual functionality is invaluable for applications that require video feeds for monitoring, visual confirmation, or the creation of video intercom systems.

Figure: Schematic diagram of the hardware composition of the AI binocular vision recognition sensor.

Features

• Binocular 3D viability detection resists spoofing by photo/video.
• Neural network-based algorithms: face recognition, palm vein recognition, QR code decoding.
• Local memory: 1,000 faces + 1,000 palm vein patterns.
• Works in total darkness and no direct sunlight outdoors.
• No host computing requirement; all AI processing takes place offline on the module.

Applications

• Smart home systems
• Smart locks
• Retail self-service payment terminals
• 3D payment systems based on facial/palm vein recognition
• Palm vein authentication systems

Package contains: 1 x Offline AI Binocular 3D Vision Recognition Sensor (Face / Palm Vein / QR Code) - DFRobot

Specifically, the kit includes:

• 1 x AI binocular vision recognition sensor (face, palm vein and QR code)
• 1 x 1.25 mm 4-pin cable with Dupont female connector
• 1 x USB data cable