@article {10.3844/jcssp.2022.78.89,
article_type = {journal},
title = {Evaluation of Transfer Learning for Mask Detection},
author = {Akram, Zahin and Arman, Arifuzzaman and Imtiaz, Mohammad Rakib and Amir, Syed Athar Bin},
volume = {18},
number = {2},
year = {2022},
month = {Mar},
pages = {78-89},
doi = {10.3844/jcssp.2022.78.89},
url = {https://thescipub.com/abstract/jcssp.2022.78.89},
abstract = {The use of masks has become crucial in combating the Coronavirus pandemic. Unfortunately, the regulation of wearing a mask is not being upheld by many citizens which is contributing to the spread of the disease. To aid the efforts of regulations and to maintain safety in public areas, both large like parks or small like public transport, Artificial Intelligent systems can play a vital role. In this article, we explore the use of transfer learning across 5 models (Mobile Net V2, InceptionV3, Resnet50V2, VGG16 and DenseNet121) and measure their effectiveness in mask detection. Due to the lack of a large, diverse and annotated dataset, we explore the use of transfer learning using supervised methods and present the results of the experiments upon the Keras open-sourced models. We find an average of 99% accuracy for all 5 models. However, when we use K-Fold Cross Validation to account for bias, we find significant differences in results with the highest accuracy being achieved by VGG16 at 98.6%. With the mixture of the standard method of training and testing alongside K-Fold Cross Validation, we present our findings for the use of transfer learning for mask detection.},
journal = {Journal of Computer Science},
publisher = {Science Publications}
}