/Mask-Detection

we don't use any face maks dataset to complete face mask Detection

Primary LanguagePython

Mask-Detection on defending 2019 novel coronavirus (2019-nCoV)

We don't use any face maks dataset to complete face mask Detection, we think mask material is similar to clothes,they are textiles.
Finally we count clothes class of pixel proportion of face to predict by segmentation network.

Dataset

Clothing Co-Parsing(CCP) dataset that i used can be found https://github.com/bearpaw/clothing-co-parsing.

Pre-Processing

After importing the image data , divide into four classes(Background, hair, skin, clothes) and resize 384 x 256.

Models

Models are found in model file. Model file includes FCN.py DeepLabV2.py, UNet.py. U-Net has shown the best performance among the models in this project.

Requirement

  • Python3
  • Keras

Usage

Then copy the annotation and photo files into the same path as pre_processing.py in the download file. After that you copy files, you can run train model.

train model and test image

python3 train.py

After,you can test your image

python3 test.py --model_path=/home/***.h5 --image_path=/home/yout_test_img_path.jpg

Pre_model link Extraction code:piwi

Result

Mask No_mask