یک رویکرد یادگیری انتقالی با شبکه عصبی کانولوشنال برای تشخیص افراد دارای ماسک از روی تصاویر

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده فنی و مهندسی میانه - دانشگاه تبریز - میانه - ایران

2 دانشکده فنی مهندسی میانه - دانشگاه تبریز - میانه - ایران

3 دانشکده فنی و مهندسی - دانشگاه مراغه - مراغه - ایران

چکیده

با توجه به همه‌گیری ویروس کرونا (کووید-۱۹) و انتقال سریع آن در سرتاسر دنیا، جهان با یک بحران بزرگ روبرو شده است. برای جلوگیری از شیوع ویروس کرونا سازمان بهداشت جهانی (WHO) استفاده از ماسک و رعایت فاصله اجتماعی در مکان‌های عمومی و شلوغ را بهترین روش پیشگیرانه معرفی کرده است. این مقاله یک سیستم برای شناسایی افراد دارای ماسک پیشنهاد می‌کند که بر پایه یادگیری انتقالی و معماری Inception v3 است. روش پیشنهادی با استفاده از دو مجموعه داده (SMFD) Simulated Mask Face Dataset و MaskedFace-Net (MFN) آموزش می‌بیند و با تنظیم بهینه فراپارامتر‌ها و طراحی دقیق بخش تمامأ متصل سعی می‌کند دقت سیستم پیشنهادی را افزایش دهد. از مزایای سیستم پیشنهادی این است که می‌تواند علاوه بر صورت‌های دارای ماسک و بدون ماسک، حالت‌های استفاده غیر صحیح از ماسک را نیز تشخیص دهد. از این‌رو روش پیشنهادی تصاویر چهره ورودی را به سه دسته تقسیم‌بندی خواهد کرد. نتایج آزمایشی، دقت و کارایی بالای روش پیشنهادی را در موضوع فوق نشان می‌دهند؛ بطوری‌که این مدل در داده‌های آموزش به دقت ٪99/47 و در داده‌های آزمایشی به دقت ٪99/33 دست یافته است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

A transfer learning approach with convolutional neural network for Face Mask Detection

نویسندگان [English]

  • Abolfzal Younesi 1
  • Reza Afrouzian 2
  • Yousef Seyfari 3
1 Miyaneh Faculty of Engineering, University of Tabriz, Miyaneh, Iran
2 Miyaneh Faculty of Engineering, University of Tabriz, Miyaneh, Iran
3 Faculty of Engineering, University of Maragheh, Maragheh, Iran
چکیده [English]

Due to the epidemic of the coronavirus (Covid-19) and its rapid spread around the world, the world has faced a huge crisis. To prevent the spread of the coronavirus, the World Health Organization (WHO) has introduced the use of masks and keeping social distance as the best preventive method. So, developing an automatic monitoring system for detection of facemask in some crowded places is essential. To do this, we propose a mask recognition system based on transfer learning and Inception v3 architecture. In the proposed method, two datasets are used simultaneously for training including: Simulated Mask Face Dataset (SMFD) and MaskedFace-Net (MFN).this paper tries to increase the accuracy of the proposed system by optimally setting hyper-parameters and accurately designing the fully connected layers. The main advantage of the proposed method is that in addition to masked and unmasked face, it can also detect cases of incorrect use of mask. Therefore, the proposed method classifies the input face images into three categories. Experimental results show the high accuracy and efficiency of the proposed method; so that, this method has achieved to accuracy of 99.47% and 99.33% in training and test data respectively. 

کلیدواژه‌ها [English]

  • Mask
  • Covid-19
  • Transfer learning
  • Convolutional neural network
  • Inception v3
[1] Cabani, K. Hammoudi, H. Benhabiles, and M. Melkemi, "MaskedFace-Net–A dataset of correctly/incorrectly masked face images in the context of COVID-19." Smart Health, vol.19, 2021.
[2] V. Militante and N. V. Dionisio, "Real-Time Facemask Recognition with Alarm System using Deep Learning," 2020 11th IEEE Control and System Graduate Research Colloquium (ICSGRC) , pp. 106-110. IEEE, 2020
[3] J. Chowdary, N. S. Punn, S. K. Sonbhadra, and S. Agarwal, “Face mask detection using transfer learning of InceptionV3,” International Conference on Big Data Analytics , pp. 81-90 Springer, Cham, 2020.
[4] Loey, G. Manogaran, M. Hamed, N. Taha, N. Eldeen, and M. Khalifa, Fighting Against COVID-19: A Novel Deep Learning Model Based on YOLOv2 with ResNet-50 for Medical Face Mask Detection” Sustainable cities and society, vol.65, 2021
[5] Shorten and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” J. Big Data, vol. 6, no. 1, 2019.
[6] Mikolajczyk and M. Grochowski, “Data augmentation for improving deep learning in image classification problem,”  In 2018 international interdisciplinary PhD workshop (IIPhDW), pp. 117-122. IEEE, 2018.
[7] C. Wong, A. Gatt, V. Stamatescu, and M. D. McDonnell, “Understanding data augmentation for classification: When to warp?,”  In 2016 international conference on digital image computing: techniques and applications (DICTA), pp. 1-6. IEEE, 2016.
[8] M. Kouw and M. Loog, “An introduction to domain adaptation and transfer learning,”  arXiv preprint arXiv:1812.11806 , 2018.
[9] J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. Knowl. Data Eng., vol. 22, no. 10, pp. 1345–1359, 2010.
[10] Hussain, J. J. Bird, and D. R. Faria, “A study on CNN transfer learning for image classification In UK Workshop on computational Intelligence, pp. 191-202. Springer, Cham, 2018.
[11] Loey, G. Manogaran, M. H. N. Taha, and N. E. M. Khalifa, “A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic,” Measurement (Lond.), vol. 167, no. 108288, p. 108288, 2021.
[12] Nagrath, R. Jain, A. Madan, R. Arora, P. Kataria, and J. Hemanth, “SSDMNV2: A real time DNN-based face mask detection system using single shot multibox detector and MobileNetV2,” Sustain. Cities Soc., vol. 66, no. 102692, p. 102692, 2021.
[13] Jiang, F. Xinqi, and Y. Hong. "Retinamask: A face mask detector." arXiv preprint arXiv:2005.03950, 2020.
[14] Ud Din, K. Javed, S. Bae, and J. Yi, “A novel GAN-based network for unmasking of masked face,” IEEE Access, vol. 8, pp. 44276–44287, 2020.
[15] I. Eyiokur, H. K. Ekenel, and A. Waibel, “Unconstrained face-mask & face-hand datasets: Building a computer vision system to help prevent the transmission of COVID-19,” arXiv preprint arXiv:2103.08773, 2021.
[16] S. Ejaz and M. R. Islam, "Masked Face Recognition Using Convolutional Neural Network," 2019 International Conference on Sustainable Technologies for Industry 4.0 (STI), pp. 1-6, 2019
[17] Yosinski, J. Clune, Y. Bengio, and H. Lipson, “How transferable are features in deep neural networks?,” Advances in neural information processing systems, vol. 27, 2014.
[18] Vasan, M. Alazab, S. Wassan, H. Naeem, B. Safaei, and Q. Zheng, “IMCFN: Image-based malware classification using fine-tuned convolutional neural network architecture,” Comput. netw., vol. 171, no. 107138, p. 107138, 2020.
[19] “Advice for the public on COVID-19 – World Health Organization,” Who.int. [Online]. Available: https://www.who.int/emergencies/diseases/novel-coronavirus-2019/advice-for-public
[20] Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features," Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, pp. I-I, 2001.
[21] Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich., “Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition”, pages 1–9, 2015
[22] Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens and Z. Wojna, "Rethinking the Inception Architecture for Computer Vision," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818-2826, 2016
[23] Weiss, T. M. Khoshgoftaar, and D. Wang, “A survey of transfer learning,” J. Big Data, vol. 3, no. 1, 2016.
[24] Keras Team, “Keras applications,” Keras.io. [Online]. Available: https://keras.io/api/applications/.
[25] Liu, C. Wang, Y. Hu, Z. Zeng, J. Bai, and G. Liao, “Transfer learning with convolutional neural network for early gastric cancer classification on magnifiying narrow-band imaging images,” In 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 1388-1392. IEEE, 2018.
[26] Arjmand, S. Meshgini and R. Afrouzian, Breast tumor detection using convolutional neural network in MRI images, Journal of Advances Signal Processing, vol. 3, no. 2, pp. 109-117, 2019
[27] M. Peyrohoseini nejad, A. Karami, Automatic small defect detection in unmanned aerial vehicle images of power transmission lines using DRSPTL, Journal of Advances Signal Processing, vol. 4, no. 2, 159-170, 2020.