[Research] 문헌조사① : Face Mask Detection

Face Mask Detection using Transfer Learning of InceptionV3

Authors

• G. Jignesh Chowdary 1 , Narinder Singh Punn 2 , Sanjay Kumar Sonbhadra 2 , and Sonali Agarwal 2

Abstract

• According to WHO, the most effective preventive measure against COVID-19 is wearing a mask in public places and crowded areas.
• In this paper, a transfer learning model is proposed to automate the process of identifying the people who are not wearing mask.
• The proposed model is built by fine-tuning the pre-trained state-of-the-art deep learning model, InceptionV3.
• The proposed model is trained and tested on the Simulated Masked Face Dataset (SMFD).

 

• Image augmentation technique is adopted to address the limited availability of data for better training and testing of the model.

• an accuracy of 99.9% during training and 100% during testing.

 

Introduction

• An initiative was started by the French government to identify passengers who are not wearing masks in the metro station. AI software was built and integrated with security cameras in Paris metro stations[2:Chowdary, G.J. et al.].
• The main aim of this work is to develop a deep learning model for the detection of persons who are not wearing face mask. (Using the transfer learning of InceptionV3)
  • Section 2 : the review of related works in the past.
  • Section 3 : describes the dataset.
  • Section 4 : describes the proposed model
  • Section 5 : presents the experimental analysis of the proposed transfer-learning model.
  • Section 6 : the conclusion of the proposed work

너무 small data set 인듯..

결과를 신뢰하기 어려운 그래프 개형,,

 

 

Conclusion

• The proposed transfer learning model achieved accuracy and specificity of 99.92%, 99.9% during training, and 100%, 100% during testing on the SMFD dataset.
• The same work can further be improved by employing large volumes of data and can also be extended to classify the type of mask, and implement a facial recognition system, deployed at various workplaces to support person identification while wearing the mask.

Insight

• InceptionV3 활용 가능성
• large data set의 필요성
• Task level
  • 1 : mask face detection
  • 2 : mask face recognition