UPES student develops Face Mask Detection System using Machine Learning

Developed using Supervised Learning paradigm and PC Web Camera to detect people with or without masks, this system can be implemented at colleges, airports, hospitals, and offices where chances of spread of COVID-19 through contagion are relatively higher

UPES student Abhinav Mudgal (B.Tech. Mechatronics batch 2017-2021) has developed a face mask detection technique using Machine Learning under the guidance of Dr. Natraj Mishra, Faculty, Department of Mechanical Engineering.

According to official data, India has a high-test positivity rate for COVID-19. Several countries lifted their lockdowns when their COVID-19 numbers started reducing, In the wake of the unlock 1.0 in India, when businesses have to go back to normal, it is essential to wear a mask for one’s own and others’ protection as well.

Dr. Mishra says, “In order to effectively prevent the spread of COVID-19, it is necessary to wear a mask. Therefore, it is urgent to improve the face recognition performance of the existing technology on masked and unmasked faces. Face mask detection platform uses Machine Learning to recognize if a user is wearing a mask or not.”

Machine Learning, at its most basic, is the practice of using algorithms to parse data, learn from it, and then decide or predict about something in the world. Machine Learning algorithms can apply what is learned in the past to new data using labelled examples to predict future events. In contrast, unsupervised Machine Learning algorithms are deployed when the information used to train is neither classified nor labelled. Abhinav adds, “Unsupervised learning studies how systems can infer a function to describe a hidden structure from unlabelled data. The system does not figure out the right output, but it explores the data and can draw inferences from datasets to describe hidden structures from unlabelled data.”

He explains further that starting from the analysis of a known training dataset, the learning algorithm produces an inferred function to make predictions about the output values. “The system is able to provide targets for any new input after sufficient training. The learning algorithm can also compare its output with the correct, intended output and find errors to modify the model accordingly,” Abhinav informs.

According to Dr. Mishra, in this project, the Face Mask Detection System has been developed using Supervised Learning paradigm and a PC Web Camera to detect people with or without masks. He says, “The masked and unmasked datasets have helped to train the model to identify whether the people are wearing masks or not.”

Abhinav further adds that the main goal of the project is to implement this system at colleges, airports, hospitals, and offices where chances of spread of COVID-19 through contagion are relatively higher. He says, “Face data of students, travellers, employees and workers will be captured in the system at the entrance. If anyone is found to be without a face mask, their picture will be sent to the authorities so that they can take quick action and the individual will receive a notification to wear a mask. The Face Mask Detection System will also monitor employees without masks and will send them a reminder to wear one.”


  1. Another Great work Abhinav…. , hope your work will help community in large for present COVID19 situation to remain safe and healthy,

    Keep it up, all the best..

  2. Great innovation and grt use of Machine Learning
    Hope this would suffice the purpose.
    we are facing face recognition problem after wearing mask.Govt should use such technology for better recognition of face.
    Kudos to inventors 👍

  3. Great inovation and kudos to inventors.
    This would help govt system and enforcement of mandatory mask wear to public in public place.

      1. Very innovative idea explore by you. With the help of this innovation people may get benefited. Keep enhancing the effectiveness of system. Go ahead

Leave a Reply

Your email address will not be published. Required fields are marked *

close slider