Contactless-Face-Mask-Recognition

Summary

In this project, a pretrained convolutional neural netwrok (CNN) is utilized for real time contactless face mask detection. The system effectively identifies faces with mask and non-mask regardless of the color of the mask. CNN is adopted to extract the meaningful features of the image input and perform the detection task. The model system achieved an overall detection accuracy of 97.6%.

real time detection from webcam/video stream

mask_recognition_thomas.mp4

Dataset Samples

With Mask	Without Mask

Requirements

- tensorflow > 1.15.2 
- keras==2.3.1
- opencv-python==4.2.0
- numpy==1.18.2
- matplotlib==3.2.1
- scipy==1.4.1
- imutils==0.5.3

Tools

• Python
• OpenCV
• Tensorflow
• Keras
• macOs BigSur Version 11.6