Madan Mohan.M et.

al Journal of Science Technology and Research (JSTAR)

Automatic Face Mask Detection Using Python

1
Madan Mohan.M, 2Sojasomanan, 3M.Kaleeswari
1
Assistant Professor, 1,2,3Department of Computer Science Engineering,
Nehru Institute of Engineering and Technology Coimbatore.
1 3
[email protected], [email protected], [email protected]

Abstract:
The corona virus COVID-19 pandemic is causing a global health crisis so the effective
protection methods is wearing a face mask in public areas according to the World Health
Organization (WHO). The COVID-19 pandemic forced governments across the world to impose
lockdowns to prevent virus transmissions. Reports indicate that wearing facemasks while at
work clearly reduces the risk of transmission. An efficient and economic approach of using AI to
create a safe environment in a manufacturing setup. A hybrid model using deep and classical
machine learning for face mask detection will be presented. A face mask detection dataset
consists of with mask and without mask images, we are going to use OpenCV to do real-time
face detection from a live stream via our webcam. We will use the dataset to build a COVID-19
face mask detector with computer vision using Python, OpenCV, and Tensor Flow and Keras.
Our goal is to identify whether the person on image/video stream is wearing a face mask or not
with the help of computer vision and deep learning.

Key words: Machine learning, R-CNN algorithm, MobilenetV2, Keras OpenCV. Face Mask
Detection.

INTRODUCTION:
The reason for this is that the virus that causes COVID-19 can be spread even before
symptoms appear, by such things as coughing, sneezing, or even speaking at close range. Cloth
face coverings have been recommended due to their low cost and ready availability. By using
cloth face coverings, it preserves surgical masks and N-95 masks for healthcare workers who
may be involved in direct care of patients with COVID-19.
Corresponding Author: M.Madan Mohan, Asst. Professor,
Department of CSE, Nehru Institute of Engineering and Technology
Coimbatore.
Mail: [email protected]

Volume No.2, Issue No.1 (2021) 91

Madan Mohan.M et.al Journal of Science Technology and Research (JSTAR)
The importance of using face coverings in public is illustrated in the graphic seen here. If
I wear my face covering to protect you from me, and you wear your face covering to protect me
from you, then we can all dramatically decrease our risk of transmission of the virus that causes
COVID-19. This, in conjunction with social distancing and frequent handwashing or use of hand
sanitizer, will be important in limiting the spread of COVID-19 as we return to our usual
activities.

The wearing of the face masks appears as a solution for limiting the spread of COVID-19.
In this context, our projects Aims to create a mask detecting system which will enable us with
the information using image processing that if a person is wearing mask on real time or not.

A face mask detection dataset consists of with mask and without mask images. we are
going to use OpenCV to do real-time face detection from a live stream via our webcam. We will
use the dataset to build a COVID-19 face mask detector with computer vision using Python,
OpenCV, and Tensor Flow and Keras. Our goal is to identify whether the person on image/video
stream is wearing a face mask or not with the help of computer vision and deep learning.

Here we introduce a mask face detection model that is based on computer vision and
deep learning. The proposed model can be integrated with surveillance cameras to impede the
COVID-19 transmission by allowing the detection of people who are wearing masks not wearing
face masks. The model is integration between deep learning and classical machine learning
techniques with OpenCV, tensor flow and Keras. We have used deep transfer learning for
feature extractions and combined it with three classical machine learning algorithms. We
introduced a comparison between them to find the most suitable algorithm that achieved the
highest accuracy and consumed the least time in the process of training and detection.

LITERATURE SURVEY
[1] An Automated System to Limit COVID-19 Using Facial Mask Detection in Smart City
Network (Base Paper):
COVID-19 pandemic caused by novel coronavirus is continuously spreading until now all
over the world. The impact of COVID-19 has been fallen on almost all sectors of development.
The healthcare system is going through a crisis. Many precautionary measures have been taken
to reduce the spread of this disease where wearing a mask is one of them. In this paper, we
propose a system that restrict the growth of COVID-19 by finding out people who are not
wearing any facial mask in a smart city network where all the public places are monitored with
Closed-Circuit Television (CCTV) cameras. While a person without a mask is detected, the

Volume No.2, Issue No.1 (2021) 92

Madan Mohan.M et.al Journal of Science Technology and Research (JSTAR)
corresponding authority is informed through the city network. A deep learning architecture is
trained on a dataset that consists of images of people with and without masks collected from
various sources. The trained architecture achieved 98.7% accuracy on distinguishing people
with and without a facial mask for previously unseen test data. It is hoped that our study would
be a useful tool to reduce the spread of this communicable disease for many countries in the
world.
[2] Case cade framework for masked face detection:
Accurately and efficiently detecting masked faces is increasingly meaningful, since it can
be applied on tracking and identifying criminals or terrorists. As a unique face detection task,
masked face detection is much more difficult because of extreme occlusions which leads to the
loss of face details. Besides, there is almost no existing large-scale accurately labeled masked
face dataset, which increase the difficulty of masked face detection. The CNN-based deep
learning algorithms has made great breakthroughs in many computer vision areas including
face detection. In this paper, we propose a new CNN-based cascade framework, which consists
of three carefully designed convolutional neural networks to detect masked faces. Besides,
because of the shortage of masked face training samples, we propose a new dataset called
"MASKED FACE dataset" to fine-tune our CNN models. We evaluate our proposed masked face
detection algorithm on the MASKED FACE testing set, and it achieves satisfactory performance.
[3] Face mask detection using Mobile Net and Global Pooling Block:
Coronavirus disease is the latest epidemic that forced an international health emergency. It
spreads mainly from person to person through airborne transmission. Community transmission
has raised the number of cases over the world. Many countries have imposed compulsory face
mask policies in public areas as a preventive action. Manual observation of the face mask in
crowded places is a tedious task. Thus, researchers have motivated for the automation of face
mask detection system. In this paper, we have presented a Mobile Net with a global pooling
block for face mask detection. The proposed model employs a global pooling layer to perform a
flatten of the feature vector. A fully connected dense layer associated with the soft max layer
has been utilized for classification. Our proposed model outperforms existing models on two
publicly available face mask datasets in terms of vital performance metrics.
[4] Study of the Performance of Machine Learning Algorithms for Face Mask Detection:
Nowadays, the situation of the Covid-19 virus still intensifying throughout the world. The
number of populations of each country is severely infected and deaths. One solution to prevent
is to wearing a masked face. Many businesses and organization need to adapt and protect an
infected person by detecting whoever does not wear masked face; however, the number of

Volume No.2, Issue No.1 (2021) 93

Madan Mohan.M et.al Journal of Science Technology and Research (JSTAR)
users or customers are more than staffs result in difficult checking. This paper studies the
performance of the three algorithms: KNN, SVM and Mobile Net to find the best algorithm
which is suitable for checking who wearing masked face in a real-time situation. The results
show that Mobile Net is the best accuracy both from input images and input video from a
camera (real-time).
[5] Face recognition based on modular histogram of oriented directional features:
This paper presents an illumination invariant face recognition system that uses local
directional pattern descriptor and modular histogram. The proposed Modular Histogram of
Oriented Directional Features (MHODF) is an oriented local descriptor that is able to encode
various patterns of face images under different lighting conditions. It employs the edge
response values in different directions to encode each sub-image texture and produces multi-
region histograms for each image. The edge responses are very important and play the main
role for improving the face recognition accuracy. Therefore, we present the effectiveness of
using different directional masks for detecting the edge responses on face recognition accuracy,
such as Prewitt kernels, Kirsch masks, Sobel kernels, and Gaussian derivative masks. The
performance evaluation of the proposed MHODF algorithm is conducted on several publicly
available databases and observed promising recognition rates.
[6] Masked Face Recognition Using Convolutional Neural Network:
Recognition from faces is a popular and significant technology in recent years. Face
alterations and the presence of different masks make it too much challenging. In the real-world,
when a person is uncooperative with the systems such as in video surveillance then masking is
further common scenarios. For these masks, current face recognition performance degrades.
An abundant number of researches work has been performed for recognizing faces under
different conditions like changing pose or illumination, degraded images, etc. Still, difficulties
created by masks are usually disregarded. The primary concern to this work is about facial
masks, and especially to enhance the recognition accuracy of different masked faces. A feasible
approach has been proposed that consists of first detecting the facial regions. The occluded
face detection problem has been approached using Multi-Task Cascaded Convolutional Neural
Network (MTCNN). Then facial features extraction is performed using the Google Face Net
embedding model. And finally, the classification task has been performed by Support Vector
Machine (SVM). Experiments signify that this mentioned approach gives a remarkable
performance on masked face recognition. Besides, its performance has been also evaluated
within excessive facial masks and found attractive outcomes. Finally, a correlative study also
made here for a better understanding.

Volume No.2, Issue No.1 (2021) 94

Madan Mohan.M et.al Journal of Science Technology and Research (JSTAR)
[7] Control The COVID-19 Pandemic:
Face Mask Detection Using Transfer Learning Currently, in the face of the health crisis
caused by the Coronavirus COVID-19 which has spread throughout the worldwide. The fight
against this pandemic has become an unavoidable reality for many countries. It is now a matter
involving many areas of research in the use of new information technologies, particularly those
related to artificial intelligence. In this paper, we present a novel contribution to help in the
fight against this pandemic. It concerns the detection of people wearing masks because they
cannot work or move around as usual without protection against COVID-19. However, there are
only a few research studies about face mask detection. In this work, we investigated using
different deep Convolutional Neural Networks (CNN) to extract deep features from images of
faces. The extracted features are further processed using various machine learning classifiers
such as Support Vector Machine (SVM) and K-Nearest Neighbors (K-NN). Were used and
examined all different metrics such as accuracy and precision, to compare all model
performances. The best classification rate was getting is 97.1%, which was achieved by
combining SVM and the MobileNetV2 model. Despite the small dataset used (1376 images), we
have obtained very satisfactory results for the detection of masks on the faces.
[8] Facial Mask Detection using Semantic Segmentation:
Face Detection has evolved as a very popular problem in Image processing and Computer
Vision. Many new algorithms are being devised using convolutional architectures to make the
algorithm as accurate as possible. These convolutional architectures have made it possible to
extract even the pixel details. We aim to design a binary face classifier which can detect any
face present in the frame irrespective of its alignment. We present a method to generate
accurate face segmentation masks from any arbitrary size input image. Beginning from the RGB
image of any size, the method uses Predefined Training Weights of VGG - 16 Architecture for
feature extraction. Training is performed through Fully Convolutional Networks to semantically
segment out the faces present in that image. Gradient Descent is used for training while
Binomial Cross Entropy is used as a loss function. Further the output image from the FCN is
processed to remove the unwanted noise and avoid the false predictions if any and make
bounding box around the faces. Furthermore, proposed model has also shown great results in
recognizing non-frontal faces. Along with this it is also able to detect multiple facial masks in a
single frame. Experiments were performed on Multi Parsing Human Dataset obtaining mean
pixel level accuracy of 93.884 % for the segmented face masks

Volume No.2, Issue No.1 (2021) 95

Madan Mohan.M et.al Journal of Science Technology and Research (JSTAR)
[9] Deep Learning Based Assistive System to Classify COVID-19 Face Mask for Human Safety
with YOLOv3:
Computer vision learning pay a high attention due to global pandemic COVID-19 to
enhance public health service. During the fatality, tiny object detection is a more challenging
task of computer vision, as it recruits the pair of classification and detection beneath of video
illustration. Compared to other object detection deep neural networks demonstrated a helpful
object detection with a superior achievement that is Face mask detection. However, accession
with YOLOv3 covered by an exclusive topic which through certainly happening natural disease
people get advantage. Added with face mask detection performed well by the YOLOv3 where it
measures real time performance regarding a powerful GPU. whereas computation power with
low memory YOLO darknet command sufficient for real time manner. Regarding the paper
section below we have attained that people who wear face masks or not, its trained by the face
mask image and nonface mask image. Under the experimental conditions, real time video data
that finalized over detection, localization and recognition. Experimental results that show
average loss is 0.0730 after training 4000 epochs. After training 4000 epochs map score is 0.96.
This unique approach of face mask visualization system attained noticeable output which has
96% classification and detection accuracy.
[10] Deep Learning Framework to Detect Face Masks from Video Footage:
The use of facial masks in public spaces has become a social obligation since the wake of
the COVID-19 global pandemic and the identification of facial masks can be imperative to
ensure public safety. Detection of facial masks in video footages is a challenging task primarily
due to the fact that the masks themselves behave as occlusions to face detection algorithms
due to the absence of facial landmarks in the masked regions. In this work, we propose an
approach for detecting facial masks in videos using deep learning. The proposed framework
capitalizes on the MTCNN face detection model to identify the faces and their corresponding
facial landmarks present in the video frame. These facial images and cues are then processed
by a neoteric classifier that utilizes. The MobileNetV2 architecture as an object detector for
identifying masked regions.
Related Work
We have collected and analyzed several years IEEE papers to get a refined visualization on face
mask detection system using different methods. Previously the system propose a new CNN-
based cascade framework, which consists of three carefully designed convolutional neural
networks to detect masked faces. Besides, because of the shortage of masked face training
samples, we propose a new dataset called "MASKED FACE dataset" to fine-tune our CNN

Volume No.2, Issue No.1 (2021) 96

Madan Mohan.M et.al Journal of Science Technology and Research (JSTAR)
models. The current study used OpenCV, Pytorch and CNN to detect whether people were
wearing face masks or not. The models were tested with images and real-time video streams.
Even though the accuracy of the model is around 60%, the optimization of the model is a
continuous process and we are building a highly accurate solution by tuning the
hyperparameters. MobileNetV2 was used to build the mobile version of the same. This specific
model could be used as a use case for edge analytics.

Proposed work:

The proposed project will be able to analyze the images through camera and detects the
presence of mask and create masked face images from unmasked face images by appending
the mask on the face recognized on the image and store it. the project works by integration of
python OpenCV tensor flow for implementing the detection of face mask.
We are using R CNN which is really efficient compared to the other machine learning model.
The data modeling and analysis tools, such as data mining, machine learning, have the potential
to generate a knowledge-rich environment which can help to significantly improve the quality
of clinical decisions. MobileNetV2 builds upon the ideas from MobileNetV1 [1], using depth
wise separable convolution as efficient building blocks. However, V2 introduces two new
features to the architecture: 1) linear bottlenecks between the layers, and 2) shortcut
connections between the bottlenecks1. The basic structure is shown below.

CONCLUSION
The current study used OpenCV, Pytorch and CNN to detect whether people were wearing face
masks or not. The models were tested with images and real-time video streams. Even though
the accuracy of the model is around 60%, the optimization of the model is a continuous process
and we are building a highly accurate solution by tuning the hyperparameters. MobileNetV2
was used to build the mobile version of the same. This specific model could be used as a use
case for edge analytics.

Volume No.2, Issue No.1 (2021) 97

Madan Mohan.M et.al Journal of Science Technology and Research (JSTAR)
As the technology are blooming with emerging trends the availability so we have novel face
mask detector which can possibly contribute to public healthcare. The architecture consists of
Mobile Net as the backbone it can be used for high and low computation scenarios. In order to
extract more robust features, we utilize transfer learning to adopt weights from a similar task
face detection, which is trained on a very large dataset. We used OpenCV, tensor flow, keras ,
Pytorch and CNN to detect whether people were wearing face masks or not. The models were
tested with images and real-time video streams. The accuracy of the model is achieved and, the
optimization of the model is a continuous process and we are building a highly accurate
solution by tuning the hyper parameters. This specific model could be used as a use case for
edge analytics. Furthermore, the proposed method achieves state-of-the-art results on a public
face mask dataset. By the development of face mask detection. we can detect if the person is
wearing a face mask and allow their entry would be of great help to the society.
REFERENCES
1. Z. Allam and D. S. Jones, “On the Coronavirus (COVID-19) Outbreak and the Smart City
Network: Universal Data Sharing Standards Coupled with Artificial Intelligence (AI) to
Benefit Urban Health Monitoring and Management,” Healthcare, vol. 8, no. 1, p. 46, 2020.
2. M. Jiang, X. Fan, and H. Yan, “Retina Mask: A Face Mask detector,” 2020. *Online+. Available:
http://arxiv.org/abs/2005.03950.
3. M. Gupta, M. Abdel Salam, and S. Mittal, “Enabling and Enforcing Social Distancing
Measures using Smart City and ITS Infrastructures. A COVID-19 Use Case,” 2020. *Online+.
Available: https://arxiv.org/abs/2004.09246.
4. J.Won Sonn and J. K. Lee, “The smart city as time-space cartographer in COVID-19 control:
the South Korean strategy and democratic control of surveillance technology,” Eurasian
Geogra , Econ., pp. 1–11, May. 2020.
5. J. W. Sonn, M. Kang and Y. Choi, "Smart city technologies for pandemic control without
lockdown", Int. J. Urban Sci., vol. 24, no. 2, pp. 149-151, 2020.
6. R. Jaiswal, A. Agarwal and R. NEGI, "Smart Solution for Reducing the COVID-19 Risk using
Smart City Technology", IET Smart Cities, vol. 2, pp. 82-88, 2020.

Volume No.2, Issue No.1 (2021) 98

Madan Mohan.M et.al Journal of Science Technology and Research (JSTAR)
7. X. Wang, X. Le and Q. Lu, "Analysis of China’s Smart City Upgrade and Smart Logistics
Development under the COVID-19 Epidemic", J. Phys. Conf. Ser., vol. 1570, pp. 012066,
2020..
8. Karthick, R., et al. “Overcome the challenges in bio-medical instruments using IOT–A
review.” Materials Today: Proceedings (2020). https://doi.org/10.1016/j.matpr.2020.08.420
9. Karthick, R., et al. “A Geographical Review: Novel Coronavirus (COVID-19) Pandemic.” A
Geographical Review: Novel Coronavirus (COVID-19) Pandemic (October 16, 2020). Asian
Journal of Applied Science and Technology (AJAST)(Quarterly International Journal) Volume
4 (2020): 44-50.
10. Sathiyanathan, N. “Medical Image Compression Using View Compensated Wavelet
Transform.” Journal of Global Research in Computer Science 9.9 (2018): 01-04.
11. Karthick, R., and M. Sundararajan. “SPIDER-based out-of-order execution scheme for Ht-
MPSOC.” International Journal of Advanced Intelligence paradigms 19.1 (2021): 28-41.
https://doi.org/10.1504/IJAIP.2021.114581
12. Sabarish, P., et al. “An Energy Efficient Microwave Based Wireless Solar Power Transmission
System.” IOP Conference Series: Materials Science and Engineering. Vol. 937. No. 1. IOP
Publishing, 2020. doi:10.1088/1757-899X/937/1/012013
13. Vijayalakshmi, S., et al. “Implementation of a new Bi-Directional Switch multilevel Inverter
for the reduction of harmonics.” IOP Conference Series: Materials Science and Engineering.
Vol. 937. No. 1. IOP Publishing, 2020. doi:10.1088/1757-899X/937/1/012026
14. Karthick, R., and M. Sundararajan. “Hardware Evaluation of Second Round SHA-3
Candidates Using FPGA (April 2, 2014).” International Journal of Advanced Research in
Computer Science & Technology (IJARCST 2014) 2.2.
15. Karthick, R., et al. “High resolution image scaling using fuzzy based FPGA implementation.”
Asian Journal of Applied Science and Technology (AJAST) 3.1 (2019): 215-221.
16. P. Sabarish, R. Karthick, A. Sindhu, N. Sathiyanathan, Investigation on performance of solar
photovoltaic fed hybrid semi impedance source converters, Materials Today: Proceedings,
2020, https://doi.org/10.1016/j.matpr.2020.08.390
17. Karthick, R., A. Manoj Prabaharan, and P. Selvaprasanth. “Internet of things based high
security border surveillance strategy.” Asian Journal of Applied Science and Technology
(AJAST) Volume 3 (2019): 94-100.
18. Karthick, R., and M. Sundararajan. “A novel 3-D-IC test architecture-a review.” International
Journal of Engineering and Technology (UAE) 7.1.1 (2018): 582-586.

Volume No.2, Issue No.1 (2021) 99

Madan Mohan.M et.al Journal of Science Technology and Research (JSTAR)
19. Karthick, R., and M. Sundararajan. “Design and implementation of low power testing using
advanced razor based processor.” International Journal of Applied Engineering Research
12.17 (2017): 6384-6390.
20. Karthick, R., and M. Sundararajan. “A Reconfigurable Method for TimeCorrelatedMimo
Channels with a Decision Feedback Receiver.” International Journal of Applied Engineering
Research 12.15 (2017): 5234-5241.
21. Karthick, R., and M. Sundararajan. “PSO based out-of-order (ooo) execution scheme for HT-
MPSOC.” Journal of Advanced Research in Dynamical and Control Systems 9 (2017): 1969.
22. Karthick, R. “Deep Learning For Age Group Classification System.” International Journal Of
Advances In Signal And Image Sciences 4.2 (2018): 16-22.
23. Karthick, R., and P. Meenalochini. “Implementation of data cache block (DCB) in shared
processor using field-programmable gate array (FPGA).” Journal of the National Science
Foundation of Sri Lanka 48.4 (2020). http://doi.org/10.4038/jnsfsr.v48i4.10340
24. Suresh, Helina Rajini, et al. “Suppression of four wave mixing effect in DWDM system.”
Materials Today: Proceedings (2021). https://doi.org/10.1016/j.matpr.2020.11.545
25. M. Sheik Dawood, S. Sakena Benazer, N. Nanthini, R. Devika, R. Karthick, Design of rectenna
for wireless sensor networks, Materials Today: Proceedings, 2021.
https://doi.org/10.1016/j.matpr.2020.11.905
26. M. Sheik Dawood, S. Sakena Benazer, R. Karthick, R. Senthil Ganesh, S. Sugirtha Mary,
Performance analysis of efficient video transmission using EvalSVC, EvalVid-NT, EvalVid,
Materials Today: Proceedings,2021. https://doi.org/10.1016/j.matpr.2021.02.287.

Volume No.2, Issue No.1 (2021) 100