This demo captures license plates using machine learning neural network algorithms to identify. The Arm® Cortex®-M4 core supports the DSP instruction to speed up algorithms. In addition, the information can be transmitted to the cloud through Wi-Fi or NB-IoT to realize the image recognition on an edge device.

• Features
  

  Board 1: Edge Computing for License Plate Recognition
  -	Supports multiple image pre-processing algorithms
  -	Supports convolutional neural network (CNN)
  -	Supports 320*240 TFT LCD Panel to show the image of original License Plate
  -	Supports Wi-Fi module to transfer the recognition result to the 2nd board
  Board 2: TFT LCD Control Board to show the recognition result
  -	Uses Wi-Fi module to receive the recognition result and show the result on the 320*240 TFT LCD Panel

• Specifications
  

  M480 (32-bit Arm® Cortex®-M4F)
  -	CPU frequency up to 192 MHz
  -	Built-in up to 512 KB Flash and 160 KB SRAM
  -	Built-in DSP Accelerator to finish the image recognition in 0.5 seconds
  -	Supports Camera capture interface and hardware binarization

• System Block Diagram