Analysis of the efficiency of recognition models in streaming video
https://doi.org/10.37493/2307-910X.2024.4.4
Abstract
This article analyzes VGG, MobileNet, and ResNet architectures for medical face mask recognition in streaming video. Deep convolutional neural network is presented by Python libraries: Tensorflow, Keras, and Haar wavelets based on the models of three architectures and their comparative analysis is performed. As a result of the study it was found that the VGGNet method has many times more parameters and is slow to work, while the fastest is Resnet, its accuracy is 97.1% for 30 epochs, and MobileNet - 98.9% for 100 epochs. But according to the results of MobileNet training, it was noticeable that its accuracy increases, and we can conclude that the accuracy will definitely improve if we train on more epochs and photo images, and its compact size allows to use it on devices with modest characteristics.
About the Authors
V. M. Goryaev
Kalmyk State University
Russian Federation
Russian Federation
Vladimir M. Goryaev – PhD in Pedagogy, Associate Professor
Elista
G. A. Mankaeva
Kalmyk State University
Russian Federation
Russian Federation
Galina A. Mankaeva – Senior Lecturer
Elista
D. B. Bembitov
Kalmyk State University
Russian Federation
Russian Federation
Dirgal B. Bembitov – Associate Professor of the Department of Theoretical Physics
Elista
+79615400560
E. V. Sumyanova
Kalmyk State University
Russian Federation
Russian Federation
Elena V. Sumyanova – Associate Professor of the Department of Experimental and General Physics
Elista
+79615486561
R. A. Bisengaliev
Kalmyk State University
Russian Federation
Russian Federation
Rustem A. Bisengaliev – Associate Professor of the Department of Experimental and General Physics
Elista
+79613948910
References
1. Nisiura KH., Kobayashi T. i dr. Otsenka bessimptomnogo sootnosheniya novykh koronavirusnykh infektsii (COVID-19)//Mezhdunarodnyi zhurnal infektsionnykh zabolevanii. 2020. t. 94. c. 154-155.
2. Prokop'ev N. YA. Meditsinskaya maska // Tekhnika. Tekhnologii. Inzheneriya. 2018. № 2 (8). c. 47- 51.
3. Viola P. and Jones M. J. Robust real-time face detection // International Journal of Computer Vision. 2004. v. 57. No. 2. P.137–154.
4. Shanmugamani R., Wenzhuo Y.. Python Reinforcement Learning: Solve complex real-world problems by mastering reinforcement learning algorithms using OpenAI Gym and Tensorflow. Packt Publishing, 2019. 496 p.
5. Krizhevsky A., Sutskever I., Hinton G. E. Imagenet classification with deep convolutional neural networks //Advances in neural information processing systems. Cambridge, Massachusetts :Published by MIT Press. 2012. p. 1097-1105.
6. Goryaev V. M., Mashtykov S. S., Bembitov D. B., Mandzhieva A. N., i dr. Analiz approksimatsii Chebysheva dlya fil'trov s konechnymi i beskonechnymi impul'snymi kharakteristikami // Sovremennye naukoemkie tekhnologii. 2021. № 11. S. 22-28.
7. Rashid T. Make Your Own Neural Network. A step-by-step gentle journey through the mathematics of neural networks, and making your own using the Python computer language. Charleston : CreateSpace Independent Publishing Platform. 2016. 222 p.
8. Dzhulli A., Pal S. Biblioteka Keras – instrument glubokogo obucheniya. Realizatsiya neironnykh setei s pomoshch'yu bibliotek Theano i TensorFlow. M.: DMK Press, 2018. 296 c.
9. Rashka S., Mirdzhalili V. Python i mashinnoe obuchenie: mashinnoe i glubokoe obuchenie s ispol'zovaniem Python, scikit-learn i TensorFlow 2, 3-e izd.: Per. s angl. SPb.: OOO "Dialektika", 2020. 848 s.
10. Tensorflow API Documentation [Ehlektronnyi resurs]. 2022. URL: https://www.tensorflow.org/api_docs/python/tf.
11. F.Sholle. Glubokoe obuchenie na Python. SPb.:Piter, 2022, 400 s.
12. Weekly J. A., Ployhart R. E. An introduction to situational judgment testing // Situational judgment tests: theory, method and application. New Jersey: LEA, 2006. p. 1–12.
13. Gonsales, R. Tsifrovaya obrabotka izobrazhenii. M.:Tekhnosfera,2012. 1104 s.
14. Goryaev V.M., Burlykov V.D., Proshkin S.N., Lidzhi-Garyaev V.V., Dzhakhnaeva E.N. ROC-krivaya i matritsa putanitsy kak ehffektivnoe sredstvo dlya optimizatsii klassifikatorov mashinnogo obucheniya // Vestnik bashkirskogo universiteta. 2023.No 1. S. 36–44. DOI: DOI: 10.33184/bulletinbsu-2023.1.4. 1.
15. Ren S, He K, Girshick R, Sun J, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks// IEEE Trans Pattern Mach Intell. 2017. No.39(6). p.1137-1149. 15. Yang G. et al. Face Mask Recognition System with YOLOV5 Based on Image Recognition//IEEE 6th International Conference on Computer and Communications (ICCC). 2020. p. 1398-1404.
16. Senthil K., Benisha J., Aathish V.. Face mask and social distance detection in CCTV video streams using ai and computer vision.// International Research Journal of Engineering and Technology (IRJET). 2021. V.08.Is.07. p. 3214-3220.
17. Orel'en ZH. Prikladnoe mashinnoe obuchenie s pomoshch'yu Scikit-Learn i TensorFlow: kontseptsii, instrumenty i tekhniki dlya sozdaniya intellektual'nykh sistem. Per. s angl. SPB.: Al'fa-kniga, 2018. 688 s.
18. Rashid T. Sozdaem neironnuyu set'. Matematicheskie idei, lezhashchie v osnove neironnykh setei, i poehtapnoe sozdanie sobstvennoi neironnoi seti na yazyke Python. M.: Vil'yams, 2018. 272 s.
19. Meier U., Schmidhuber J. Multi-column deep neural networks for image classification // Computer Vision and Pattern Recognition (CVPR). IEEE Conference on. 2012. p. 3642-3649.
20. Howard, A. G. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications / A. G. Howard// CoRR. 2017. arXiv:№ 1704.04861. 9 p.
21. Shumskii S.A. Mashinnyi intellekt. Ocherki po teorii mashinnogo obucheniya i iskusstvennogo intellekta. M.: RIOR, 2019. 340 s.
22. Da-Wen Sun Computer Vision Technology for Food Quality Evaluation / Edited by Da-Wen Sun. Sandiego: Academic Press, 2016. 635 p.
23. Zheltov S.YU. i dr. Obrabotka i analiz izobrazhenii v zadachakh mashinnogo zreniya. M.: Fizmatkniga, 2010. 672 s.
24. Novikova, N.M. Raspoznavanie izobrazhenii s pomoshch'yu svertochnoi neironnoi seti i nechetkogo gibridnogo klassifikatora / N.M. Novikova, V.M. Dudenkov // Neirokomp'yutery: razrabotka, primenenie. M.: Radiotekhnika, 2015. № 2. S. 43-47.
Review
For citations:
Goryaev V.M., Mankaeva G.A., Bembitov D.B., Sumyanova E.V., Bisengaliev R.A. Analysis of the efficiency of recognition models in streaming video. Modern Science and Innovations. 2024;(4):43-52. (In Russ.) https://doi.org/10.37493/2307-910X.2024.4.4
Views:
91
Email this article 