README.md

Face detection & recognition

---

Table of Contents

• Pre-requisites
• Quick Start
• Usage
  • Dataset
  • Face Detection
  • Pre-trained Model
• Sample Outputs
• References

Pre-requisites

• argparse

  pip install argparse

• opencv-python

  pip install opencv-python

• opencv-contrib-python

  pip install opencv-contrib-python

• Numpy

  pip install numpy

• facenet-pytorch

  pip install facenet-pytorch

• Pytorch

  go to install pytorch(_version check!!)

Quick Start

• Clone this repository: $ git clone https://github.com/jaehwan-AI/face_detection_recognition

• Run the demo:

image input

$ python demo.py --image data/image/image.jpg

video input

$ python demo.py --video data/video/video.mp4

webcam

$ python demo.py --src 0

Usage

Dataset

We used Korean dataset that can't be disclosed for security reasons.

Face Detection

We used MTCNN as a facial recognition technology to analyze emotions. MTCNN uses image pyramids by resizing images entered on different scales to recognize faces of different sizes in the images.

Pre-trained Model

In order to inference the model, we used pre-learned weights using EfficientNet(2019).

Sample Outputs

sample image:

sample video:

sample webcam:

References

1. Tim Esler's facenet-pytorch repo: https://github.com/timesler/facenet-pytorch

2. Octavio Arriaga's pre-trained model repo: https://github.com/oarriaga/face_classification

3. K. Zhang, Z. Zhang, Z. Li and Y. Qiao. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks, IEEE Signal Processing Letters, 2016. PDF

4. M. Tan, Quoc V. Le. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, 2019. PDF