Data Sprint #6: Face Mask Detection
Coronavirus has now become the talk of the town, most people in the world right now are suffering badly and every day thousands of people are dying because of COVID-19. As per WHO, face masks combined with other preventive measures such as frequent hand-washing and social distancing help slow down the spread of the coronavirus.
As you might be aware, WHO has recommended that even healthy people should wear masks when venturing out of their homes into places where it is difficult to maintain distance from other people.
Imagine a local housing community has started capturing images of individuals at the entrance/exit gates, public places in and around the housing society. With this image dataset, they want to identify whether an individual in the community has worn a mask or not. Identifying the individuals would further help them to create awareness about the importance of wearing a mask to the specific set of individuals who are not complying to it. Imagine you are leading the efforts to classify images, build a machine/deep learning model to detect face masks.
Submissions are evaluated using Accuracy Score.
How do we do it?
Once you generate and submit the target variable predictions on the test dataset, your submissions will be compared with the true values of the target variable.
The True or Actual values of the target variable are hidden on the DPhi platform so that we can evaluate your model's performance on unseen data. Finally, an accuracy score for your model will be generated and displayed.
Start Date: 11th September 2020, 21:00 hours IST / 17:30 hours CET (please locate your time here)
End Date: 20th September 2020, 21:00 hours IST / 17:30 hours CET (please locate your time here)
Do you like to understand the problem through code?
Don't worry! Understand through code! Here is your getting started code
About the Data
The training dataset consists of 11,264 medium quality face images belonging to two categories - with_mask (i.e. face is covered with mask) and without_mask (no mask on the face).
From the above link you will be able to download a zip file named ‘face_mask_detection.zip’. After you extract this zip file, you will get four files:
- train - contains all the images to be used for building the model.
- Training_set_face_mask - contains the target value for each of the images in the train folder with their corresponding image name
- test - contains all the images for whose the predictions of the labels/target are to be submitted on DPhi platform
- Testing_set_face_mask - all the names of the images in the test folder are placed in an order in this csv file. The predictions of the images are to be submitted in the same order as specified in this csv file.
The images are downloaded from multiple sources like Google images, pexels.com, etc. The images used in this data science challenge is only for educational purposes.
To participate in this challenge either you have to create a team of atleast None members or join some team