/mask-detector

AI model of Mask Recognition Project conducted during the "Image Analysis" class offered by Télecom SudParis.

Primary LanguagePython

Face Mask Detector

AI model of Mask Recognition Project conducted during the "Deep Learning" class offered by Télecom SudParis. The final model contains a real-time face mask detector using Tensorflow, Keras, and OpenCV with your webcam.

Dataset

The dataset used is provided by Prajna Bhandary (https://github.com/prajnasb/). It contains 1376 images divided into with mask and without mask

Image Classifier

  • Built using the VGG16 CNN Architecture with layers added on top of the base model through transfer learning.

Results

  • The following results were obtained using our model for artificially generated masks and real masks. Screen Shot 2023-11-04 at 6 56 08 PM

  • Real life examples were made using the faces of our group members to showcase the model's accuracy: Screen Shot 2023-11-04 at 6 43 59 PM Screen Shot 2023-11-04 at 6 44 05 PM

Video Classifier

  • Built using the MTCNN model for image finding on each frame, a scale-invariant method.

Results