Comparison of the Effectiveness of Deep Learning Methods for Face Mask Detection
Bibliographic record
Abstract
The usage of mask is necessary for the prevention and control of COVID-19 which is a respiratory disease that passes from person to person by contact and droplets from the respiratory tract. It is an important task to identify people who do not wear face mask in the community. In this study, performance comparison of the automated deep learning based models including the ones that use transfer learning for face mask detection on images was performed. Before training deep models, faces were detected within images using multi-task cascaded convolutional network (MTCNN). Images obtained from face mask detection dataset, COVID face mask detection dataset, mask detection dataset, and with/without mask dataset were used for training and testing the models. Face areas that are detected with MTCNN were used as input for convolutional neural network (CNN), MobileNetV2, VGG16 and ResNet50. VGG16 showed best performance with 97.82% accuracy. MobileNetV2 showed the worst performance for detecting faces without mask with 72.44% accuracy. Comparison results show that VGG16 can be used effectively to detect faces without mask. This system can be used in crowded public areas to warn people without mask that may help the reduce the risk of pandemic.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".