2017 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation And 2017
DOI: 10.1109/iccis.2017.8274819
|View full text |Cite
|
Sign up to set email alerts
|

A cascade framework for masked face detection

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
25
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 82 publications
(25 citation statements)
references
References 15 publications
0
25
0
Order By: Relevance
“…where TP, TN, FP and FN denote the true positive, true Table I compares our proposed framework to the cascaded framework used in [12]. The higher accuracy of the cascaded framework is due to the fact that it was designed to work on images rather than videos.…”
Section: B Experimental Results and Statisticsmentioning
confidence: 99%
See 2 more Smart Citations
“…where TP, TN, FP and FN denote the true positive, true Table I compares our proposed framework to the cascaded framework used in [12]. The higher accuracy of the cascaded framework is due to the fact that it was designed to work on images rather than videos.…”
Section: B Experimental Results and Statisticsmentioning
confidence: 99%
“…The higher accuracy of the cascaded framework is due to the fact that it was designed to work on images rather than videos. Also, the "MASKED FACE" dataset [12] which was used to test the cascaded framework comprises of people wearing head gear. On the other hand, the dataset used to evaluate our proposed framework captures the various types of face masks worn by the public as a precautionary measure for disease control.…”
Section: B Experimental Results and Statisticsmentioning
confidence: 99%
See 1 more Smart Citation
“…As can be seen from the analysis of existing developments in the field of medical mask recognition, most approaches are based on neural network methods [1,2,3]. The main difference between the proposed method and the existing ones is the use of pre-trained weights on faces to initialize the neural network before training, which significantly increases both the learning speed (up to 10 epochs) and the quality of the classifier.…”
Section: Comparison With Other Methodsmentioning
confidence: 99%
“…Finally, there is also a comparative study for better understanding. In [3], the authors propose a new cascade structure based on convolutional neural networks, which consists of three carefully designed convolutional neural networks for detecting masked faces. The authors in their work talk about the applicability of the algorithm for tracking and identifying criminals or terrorists.…”
Section: Introductionmentioning
confidence: 99%