Covid Face Mask Detection.

Department of AI & Ds

Progressive Education Society MCOE, Pune. 

 Developers :-

Shankar Karande 

shankarkarande440@gmail.com

Abstract:-

The novel Coronavirus had brought a new normal life in which the social distance and wearing of face masks plays a vital role in controlling the spread of virus. But most of the people are not wearing face masks in public places which increases the spread of viruses. This may result in a serious problem of increased spreading. Hence to avoid such situations we have to scrutinize and make people aware of wearing face masks. Humans cannot be involved for this process, due to the chance of getting affected by corona.

Hence here comes the need for artificial intelligence(AI), which is the main theme of our project. Our project involves the identification of persons wearing face masks and not wearing face masks in public places by means of using image processing and AI techniques.    

Introduction :-

In this project, we have developed a deep learning model for face mask detection using Python, Keras, and OpenCV. We developed the face mask detector model for detecting whether person is wearing a mask or not. We have trained the model using Keras with network architecture. Training the model is the first part of this project and testing using webcam using OpenCV is the second part.

Also, in this project we will use Arduino Nano R3, Buzzer and LED. When person is not wearing mask then it will detect and show the red square box as well as display accuracy and display text message like No Mask around that person face and buzzer will on. When person is wearing mask then it will detect and show the green square box around that person face and display the text message like Mask as well as display accuracy on that square box and start blinking the green LED.

Hardware Requirement :-

• Webcam
• Arduino Nano R3
• LED
• Buzzer

Software Requirements :-

• Python 3.10.0
• TensorFlow
• OpenCV
• Arduino IDE
• Jupyter Notebook

Methodology :-

Step-1 :-

You will create a neural network model with TensorFlow and will train it on a dataset of both people who are wearing facemasks and people who are not.

TensorFlow is an open-source library developed by Google primarily for deep learning applications. It also supports traditional machine learning. TensorFlow was originally developed for large numerical computations without keeping deep learning in mind.

Download dataset from here :- Dataset

Step-2 :-

In training phase we are finding training loss and accuracy of our model by using dataset with mask and without mask. After completing our training model we will able to see our model accuracy trough graph chart.

Deep Learning consists of a very enormous number of neural networks that use the multiple cores of a process of a computer and video processing cards to manage the neural network’s neuron which is categorized as a single node. Deep learning is used in numerous applications because of its popularity especially in the field of medicine and agriculture.

Here, you will create a face recognition algorithm that will be able to detect facemasks on people's faces using the trained model in the previous step. if you don't have the GPU power or the needed dependencies or knowledge to work with neural network models. I have included my pre-trained model that can be used in this step without going by step 1. name of the model fil: mask_detector.model.

Step-3 :-

Finally, you will add a simple Serial Command to the facemask detection algorithm that will order the Arduino to switch LED and Buzzer on or off based on the state of detection.

Block Diagram :-

Output :-

Advantages :- 

1. Save lives.
2. Be safe from spreading.

Conclusion :-

The ensemble approach not only helps in achieving high accuracy but also improves detection speed considerably. Furthermore, the application of transfer learning on pretrained models with extensive experimentation over an unbiased dataset resulted in a highly robust and low-cost system. The identity detection of faces, violating the mask norms further, increases the utility of the system for public benefits.

Feature Scope :-

• Firstly, the proposed technique can be integrated into any high-resolution video surveillance devices and not limited to mask detection only. Secondly, the model can be extended to detect facial landmarks with a facemask for biometric purposes.

• Also, in future we will able find maximum and minimum those faces will wearing mask and without mask and sending mail to that authorized person i.e.– Manager, Boss , CEO , MD.

References :-

• A. Das, M. Wasif Ansari and R. Basak, (2020) "Covid-19 Face Mask Detection Using TensorFlow, Keras and OpenCV," 2020 IEEE 17th India Council International Conference (INDICON), New Delhi, India, pp. 1-5.

• M. Loey, G. Manogaran, M. H. N. Taha, and N. E. M. Khalifa, “A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic,” Measurement, vol. 167, Article ID 108288, 2021.

• M. Loey, G. Manogaran, M. H. N. Taha, and N. E. M. Khalifa, “A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic,” Measurement, vol. 167, Article ID 108288, 2021.

• Liu, C., and Wechsler, H. (2002). Gabor feature-based classification using the enhanced fisher linear discriminant model for face recognition. IEEE Transactions on Image processing, 11(4), 467-476.

• Liu, C., and Wechsler, H. (2002). Gabor feature-based classification using the enhanced fisher linear discriminant model for face recognition. IEEE Transactions on Image processing, 11(4), 467-476.

* GitHub Project Link :-  Click Here *