ma-shamshiri/Face-Mask-Detection

This project introduces a system that employs advanced image processing and computer vision techniques to identify unique features in images and match them with corresponding features in other images.

Face-Mask-Detection

The main objective of this project is to detect discriminating features in an image and find the best matching features in other images. Because features should be reasonably invariant to translation, rotation, and illumination.

Table of Contents

1. Prerequisites
2. How to Use
3. Results
4. Reference
5. Credits

Prerequisites

1. Open a Command Prompt (NOT Windows PowerShell) or a Terminal
2. Create a conda environment conda create -n is python=3.6.6 -y
3. Activate this environment activate is (Windows) or source activate is (Linux/macOS)
4. Install the following packages tensorflow, keras, opencv, matplotlib, numpy, pandas, scikit-learn, and notebook:
   
   
   • Python (3.6)
   • TensorFlow (2.3.2) - pip install tensorflow==2.3.2
   • Keras (2.1.6) - pip install keras==2.1.6
   • OpenCV (4.4.0) - pip install opencv==4.0.0
   • Matplotlib (3.5.1) - pip install matplotlib==3.5.1
   • Sklearn (0.23.2) - pip install scikit-learn==0.23.2
   • Jupyter (4.7.1) - pip install notebook

How to Use

* Step 1. Download Code as Zip OR

git clone https://github.com/ma-shamshiri/Face-Mask-Detection.git

Step 2. Create a new virtual environment

python -m venv tfod #window
virtualenv tfod #Linux

Step 3. Activate your virtual environment

source tfod/bin/activate # Linux
.\tfod\Scripts\activate # Windows 

Step 4. Install dependencies and add virtual environment to the Python Kernel

python -m pip install --upgrade pip
pip install ipykernel
python -m ipykernel install --user --name=tfodj

Step 5. Collect images and ensure you change the kernel to the virtual environment.

Step 6. Manually divide collected images into two folders train and test. So now all folders and annotations should be split between the following two folders.

workspace\images\train
workspace\images\test

Step 7. Begin training process by opening 2. Training and Detection.ipynb, this notebook will walk you through installing Tensorflow Object Detection, making detections, saving and exporting your model.

Step 8. During this process the Notebook will install Tensorflow Object Detection. You should ideally receive a notification indicating that the API has installed successfully at Step 8 with the last line stating OK.

Results

References

Credits

Mohammad Amin Shamshiri