INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
During the COVID-19 pandemic, the facemask detection model has become the most important and necessary model. Manually checking whether individuals are wearing facemasks in public and busy places is time-consuming and inefficient, thereby increasing exposure to the virus. Using computer vision and deep learning, we want to create an automated model that recognises whether people are wearing facemasks.In general, the majority of the publications concentrated on face detection utilizing some models and algorithms. The focus of our study is on determining whether or not people are wearing masks (detecting masks) to aid in the reduction of COVID-19 transmission and dissemination. We have found that there exist many methods to detect faces and masks with more than 90%. We aim to make a deep learning project aimed at achieving above 90% accuracy. We decided to utilize Tensorflow and OpenCV (python) to construct a face mask recognition system using Deep Learning after reading numerous research papers and comparing the accuracy and performance of the different models employed in them. We would use Convolutional Neural Network since it performs better than other models. In addition, we would construct a Keras (Python) model to compare performance with the Tensorflow model.
Keywords:
CNN (Convolutional Neural Network), Keras, Open CV ,Tensor Flow.
Cite Article:
"MaskNet: Deep Learning-based Face Mask Detection System using Convolutional Neural Networks", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 4, page no.954 - 960, April-2023, Available :http://www.ijsdr.org/papers/IJSDR2304162.pdf
Downloads:
000337211
Publication Details:
Published Paper ID: IJSDR2304162
Registration ID:205075
Published In: Volume 8 Issue 4, April-2023
DOI (Digital Object Identifier):
Page No: 954 - 960
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn