Human Face Identification

Lattice sensAI Demo

Programmable Solution- This demo, implemented on a Lattice ECP5 low-power FPGA, uses machine learning to identify different human faces. A Convolutional Neural Network (CNN) acceleration engine is trained to achieve accurate identification by extracting 256 16-bit characteristics from each registered face.

In field registration- The demo can register and identify faces without retraining, eliminating the need for uploading images and lengthy retraining using a GPU.

Rapid Implementation- The demo utilizes the Embedded Vision Development Kit, RTL blocks for the 8-layer CNN accelerator, image sensor connectivity and setup, image sensor processor and memory management are provided for easy modification.

Features

  • VGG8-like CNN trained to detect measurement points on a human face
  • In-field new face registration and identification without the need to retrain the network
  • Up to 30 frames per second
  • Power consumption:0.85 W

Jump to

Block Diagram

Documentation

Quick Reference
Downloads
TITLE NUMBER VERSION DATE FORMAT SIZE
EVDK Based Human Face Identification Demostration Bitstream User Guide
FPGA-UG-02092 1.0 9/9/2019 PDF 1.7 MB
TITLE NUMBER VERSION DATE FORMAT SIZE
EVDK Based Human Face Identification Demostration Bitstream
1.0 9/9/2019 ZIP 12 MB


Like most websites, we use cookies and similar technologies to enhance your user experience. We also allow third parties to place cookies on our website. By continuing to use this website you consent to the use of cookies as described in our Cookie Policy.