Skip to content

Latest commit

 

History

History
43 lines (34 loc) · 1.71 KB

README.md

File metadata and controls

43 lines (34 loc) · 1.71 KB

Face Mask Detector

It detect's whether the persons are wearing mask or not.

Demo

It is built with the following frameworks and libraries using the concepts of Computer Vision and Deep Learning.

Frameworks:

  • Tensorflow as Deep Learning

Libraries:

  • OpenCV
  • Matplotlib
  • Sklearn
  • NumPy
  • Seaborn
  • mtcnn

Installation Guides:

Note: You must have python 3.x installed in your system.

  • Download the zip file of this repository or clone the repository using git
  • Make a new virtual-environment(recommended)
  • Install dependencies an libraries using pip install -r requirements.txt

Training/Testing Guides:

  • Datasets are available in both splitted(train/val/test) and unsplitted form.
  • Here, I am using unsplitted datasets.
  • Dataset credit goes to Prajna Bhandary because she created this datasets.
  • Then go along the notebook Face_Mask_Detection_VGG16.py
  • It is trained with VGG16 network model. VGG16 is a convolutional neural network model proposed by K. Simonyan and A.Find more about VGG16 here
  • Perform hyperparameter tuning to get more accurate model.

Working Guides:

  • Open terminal/command prompt inside the downloaded/cloned directory
  • Run python script face_mask_detection_on_realtime.py
    • Enter python face_mask_detection_on_realtime.py in terminal
  • Your webcam will open,test it by wearing mask
  • It will detect face-mask in real-time