Mask Detection Method Based on YOLO-GBC Network

Round 1

Reviewer 1 Report

In this paper, the authors present “Mask detection method based on YOLO-GBC network.” The experimental results show that the average accuracy (mAP) of the YOLO-GBC reached 91.2% in the mask detection data set, which is 2.3% higher than the baseline YOLOv5, and the detection speed reached 64FPS. The accuracy and recall have also been improved to varying degrees, contenting the detection task of correctly wearing masks. However, there are some issues should be addressed.

1. From the structure of PAN and FPN, each input of PAN is the feature information processed by FPN, which is easy to lose the original feature information in feature fusion and affecting the detection effect. How to solve this problems?

2. How to solve the problem of information overload when computing power is limited?

3. In view of the problems of large-scale changes, background interference, and serious occlusion in the target region, the YOLOv5 network cannot satisfy the existing detection demands. How to solve the problems?

4. How to solve the problems of loss of important information and insufficient cross-latitude feature interaction in the detection process?

5. How to solve the problem of insufficient feature fusion and easy loss of target information in this paper?

6.  YOLOv5 uses the method of NMS to screen candidate frames. If the real target appears in the overlapping zone, the object detection will fail, thus reducing the average detection rate of the algorithm. How to solve the problem?

7.  How to solve the problem of incorrect deletion of candidate frames in this paper?

8.  How to solve the problem of missed detection and false detection of YOLOv5 detection algorithm?

Author Response

Dear reviewer:
We sincerely thank you for your time and effort in reviewing our manuscript (ID: electronics-2118538），titled: Mask Detection Method Based on YOLO-GBC Network.
Your comments are really thoughtful and helpful. This is very important for our work. Therefore, we have completely revised the manuscript according to your comments. Some parts are colored to make the revision more noticeable.
We hope that reviewer is satisfied with the revision of the original manuscript.
Thanks and best regards!
Yours faithfully,
Cao Yuan

Author Response File: Author Response.pdf

Reviewer 2 Report

They proposed "Mask detection method based on YOLO-GBC network"

The developed YOLO-GBC algorithm is interesting and useful for the society,  Global Attention Mechanism and Content-Aware Reassembly of Features (CARAFE) Hybrid algorithms has been proposed with the Accuracy of 91%.

The work need to improved by incorporating the following points: 

1.  Motivation of the work is missing in the introduction Section.

2.  Related work is very short, it is not updated thoroughly, So Latest work related to this domain need to be added to prove their point. Also add the following work:-

Nagrath, P., Jain, R., Madan, A., Arora, R., Kataria, P., & Hemanth, J. (2021). SSDMNV2: A real time DNN-based face mask detection system using single shot multibox detector and MobileNetV2. Sustainable cities and society, 66, 102692.

doi:10.1515/jisys-2022-0011

Pooja, S., & Preeti, S. (2021). Face mask detection using AI. In Predictive and Preventive Measures for Covid-19 Pandemic (pp. 293-305). Springer, Singapore.

Loey, M., Manogaran, G., Taha, M. H. N., & Khalifa, N. E. M. (2021). A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic. Measurement, 167, 108288.

https://doi.org/10.1007/978-981-16-3690-5_136

3. Why hybrid model is used ? Compare the Proposed work with the existing model ?

4. Improve the Conclusion, add the future work.

5. References must be cited in the text and also add the latest work.

Author Response

Dear reviewer:
We sincerely thank you for your time and effort in reviewing our manuscript (ID: electronics-2118538），titled: Mask Detection Method Based on YOLO-GBC Network.
Your comments are really thoughtful and helpful. This is very important for our work. Therefore, we have completely revised the manuscript according to your comments. Some parts are colored to make the revision more noticeable.
We hope that reviewer is satisfied with the revision of the original manuscript.
Thanks and best regards!
Yours faithfully,
Cao Yuan

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The authors have solved the related problems. It is good enough.