Face Mask Detection

Face Mask Detection System built with OpenCV, Keras/TensorFlow using Deep Learning and Computer Vision concepts in order to detect face masks in static images as well as in real-time video streams.

�� Support me here!

�� Motivation

Amid the ongoing COVID-19 pandemic, there are no efficient face mask detection applications which are now in high demand for transportation means, densely populated areas, residential districts, large-scale manufacturers and other enterprises to ensure safety. The absence of large datasets of ‘with_mask’ images has made this task cumbersome and challenging.

PPT and Project Report sharing costs ₹1000 ($15)

If interested, contact me at chandrikadeb7@gmail.com

�� Purchase at a Discounted Rate

⌛ Project Demo

�� YouTube Demo Link

�� Dev Link

⚠️ TechStack/framework used

• OpenCV
• Caffe-based face detector
• Keras
• TensorFlow
• MobileNetV2

⭐ Features

Our face mask detector doesn't use any morphed masked images dataset and the model is accurate. Owing to the use of MobileNetV2 architecture, it is computationally efficient, thus making it easier to deploy the model to embedded systems (Raspberry Pi, Google Coral, etc.).

This system can therefore be used in real-time applications which require face-mask detection for safety purposes due to the outbreak of Covid-19. This project can be integrated with embedded systems for application in airports, railway stations, offices, schools, and public places to ensure that public safety guidelines are followed.

�� Dataset

The dataset used can be downloaded here - Click to Download

This dataset consists of 4095 images belonging to two classes:

• with_mask: 2165 images
• without_mask: 1930 images

The images used were real images of faces wearing masks. The images were collected from the following sources:

• Bing Search API (See Python script)
• Kaggle datasets
• RMFD dataset (See here)

�� Prerequisites

All the dependencies and required libraries are included in the file requirements.txt See here

��   Installation

1. Clone the repo

$ git clone https://github.com/chandrikadeb7/Face-Mask-Detection.git

2. Change your directory to the cloned repo

$ cd Face-Mask-Detection

3. Create a Python virtual environment named 'test' and activate it

$ virtualenv test

$ source test/bin/activate

4. Now, run the following command in your Terminal/Command Prompt to install the libraries required

$ pip3 install -r requirements.txt

�� Working

1. Open terminal. Go into the cloned project directory and type the following command:

$ python3 train_mask_detector.py --dataset dataset

2. To detect face masks in an image type the following command:

$ python3 detect_mask_image.py --image images/pic1.jpeg

3. To detect face masks in real-time video streams type the following command:

$ python3 detect_mask_video.py 

�� Results

Our model gave 98% accuracy for Face Mask Detection after training via tensorflow-gpu==2.5.0

We got the following accuracy/loss training curve plot

Streamlit app

Face Mask Detector webapp using Tensorflow & Streamlit

command

$ streamlit run app.py 

Images

Upload Images

Results

�� And it's done!

Feel free to mail me for any doubts/query �� chandrikadeb7@gmail.com

Internet of Things Device Setup

Expected Hardware

• Raspberry Pi 4 4GB with a case
• 5MP OV5647 PiCamera from Arducam

Getting Started

• Setup the Raspberry Pi case and Operating System by following the Getting Started section on page 3 at documentation/CanaKit-Raspberry-Pi-Quick-Start-Guide-4.0.pdf or https://www.canakit.com/Media/CanaKit-Raspberry-Pi-Quick-Start-Guide-4.0.pdf
  • With NOOBS, use the recommended operating system
• Setup the PiCamera
  • Assemble the PiCamera case from Arducam using documentation/Arducam-Case-Setup.pdf or https://www.arducam.com/docs/cameras-for-raspberry-pi/native-raspberry-pi-cameras/5mp-ov5647-cameras/
  • Attach your PiCamera module to the Raspberry Pi and enable the camera

Raspberry Pi App Installation & Execution

Run these commands after cloning the project

�� Awards

Awarded Runners Up position in Amdocs Innovation India ICE Project Fair

�� Cited by:

1. https://osf.io/preprints/3gph4/
2. https://link.springer.com/chapter/10.1007/978-981-33-4673-4_49
3. https://ieeexplore.ieee.org/abstract/document/9312083/
4. https://link.springer.com/chapter/10.1007/978-981-33-4673-4_48
5. https://www.researchgate.net/profile/Akhyar_Ahmed/publication/344173985_Face_Mask_Detector/links/5f58c00ea6fdcc9879d8e6f7/Face-Mask-Detector.pdf

�� Appreciation

Selected in Devscript Winter Of Code

Selected in Script Winter Of Code

Seleted in Student Code-in

�� Credits

• https://www.pyimagesearch.com/
• https://www.tensorflow.org/tutorials/images/transfer_learning

�� Contribution

Please read the Contribution Guidelines here

Feel free to file a new issue with a respective title and description on the the Face-Mask-Detection repository. If you already found a solution to your problem, I would love to review your pull request!

�� Our Contributors

�� Code of Conduct

You can find our Code of Conduct here.

�� Citation

You are allowed to cite any part of the code or our dataset. You can use it in your Research Work or Project. Remember to provide credit to the Maintainer Chandrika Deb by mentioning a link to this repository and her GitHub Profile.

Follow this format:

• Author's name - Chandrika Deb
• Date of publication or update in parentheses.
• Title or description of document.
• URL.

❤️ Owner

Made with ❤️   by Chandrika Deb

�� License

MIT © Chandrika Deb