RK3399 SoM (System on Module) Applied in Facial Recognition Solution

FET3399-C Core Board With AI Face Recognition

AI has been a hot issue characterized by facial recognition in recent years, especially in this special year of 2020 because of the Novel Pandemic COVID-19 spreading all over the world. A facial recognition system has been used by communities, business buildings, and other public places for contactless temperature measurement, which can highly reduce people-to-people contact risk, improve efficiency, and cut down manual costs.

Here firsly let's learn what is facial recognistion system and how it works.

Facial recognition is a category of biometric software that maps an individual's facial features mathematically and stores the data as a faceprint. The software uses deep learning algorithms to compare a live capture or digital image to the stored faceprint in order to verify an individual's identity.

The software identifies 80 nodal points on a human face. In this context, nodal points are endpoints used to measure variables of a person’s face, such as the length or width of the nose, the depth of the eye sockets and the shape of the cheekbones. The system works by capturing data for nodal points on a digital image of an individual’s face and storing the resulting data as a faceprint. The faceprint is then used as a basis for comparison with data captured from faces in an image or video.

Target Application

  1. 1. Company or home access system;
  2. 2. E-pass port, identity card system;
  3. 3. Policy, legal system, creminal investigation system;
  4. 4. Self-service terminal.

Solution Frame

Recommended platform and reason

  1. 1. The processor should be powerful enough for facial recognition and infrared thermometering, RK3399 is a powerful processor integrated with GPU;
  2. 2. Cost efficient;
  3. 3. Multiple high speed USB ports for camera pheripheral. RK3399 has four native USB ports, 2x USB2.0 host and 2x USB3.0

Forlinx SoM FET3399-C Features

  • SoM FET3399-C is designed based on RK3399;
  • It integrates with 2x Cortex-A72 core@ 1.8GHz and 4x Cortex-A53@ 1.4GHz core;
  • GPU Mali-zt864, can support OpenGL ES1.1/2.0/3.0/3.1, OpenVG1.1, OpenCL, DX11;
  • On-board 2GB LPDDR3 RAM and 16GB eMMC;
  • Multiple display ports including HDMI2.0, MIPI-DSI, eDP1.3, DP1.2, resolution up to 4K, can support dual-screen playing synchoronously and asynchoronously;
  • Various peripherals such as PCIe, USB3.0 host, Type-C, MIPI CSI, SPDIF, IIC, SPI, UART, ADC, PWM, GPIO, IIS and Gigabit Ethernet port.