This project is based on Firebase ML Kit Face Detection.

The face recognition model used in this example is JHFace. Which is heavily based on arcface-tf2 implementation.

This project is trained on MS-Celeb-1M dataset, using MobileNetV2 as backbone, ArcFace for loss function. Then used IJB-C dataset for extracting centroid for every subjects, applied cosine similarity for face matching.

I'm now working on uploading tutorials on making this project. Already wrote it down in markdown in Korean on my github page I'll provide English version soon.