+7 (495) 957-77-43

T-Comm_Article 4_4_2020

Извините, этот техт доступен только в “Американский Английский”. For the sake of viewer convenience, the content is shown below in the alternative language. You may click the link to switch the active language.

DESIGNING A SUBSYSTEM OF FACE DETECTION AND DATABASE INTERFACE IN THE HARDWARE-SOFTWARE COMPLEX OF BIOMETRIC IDENTIFICATION BASED ON NEURAL NETWORK FACE RECOGNITION

Vyacheslav I. Voronov, Moscow Technical University of Communications and Informatics, Moscow, Russia, vorvi@mail.ru
Alexey D. Bykov, Moscow Technical University of Communications and Informatics, Moscow, Russia, 79778742616@yandex.ru
Lilia I. Voronova, Moscow Technical University of Communications and Informatics, Moscow, Russia, voronova.lilia@yandex.ru

Abstract
The task of biometric identification of a person is extremely urgent and can be solved in many ways. It is possible by a number of static and dynamic characteristics such as: papillary finger pattern, hand geometry, iris, face geometry (2D and 3D), vein pattern, handwriting, silhouette, gait, voice. Given the extreme growth in the number of available digital video and photo cameras in public places, a serious improvement in the quality of the data received, reducing the cost of receiving, processing and transmitting them, have received an impetus to develop methods for identifying people by video and photo images. At the same time, the vast majority of methods focus on facial recognition. The largest companies in the world are developing their own software solutions that implement facial recognition functionality in photos and video stream, and offer the market ready-made competitive solutions. All these solutions use their own set of methods and algorithms, while the use of neural networks has become a de facto industry standard, because the methods provide the fastest and most accurate results. Despite the complexity of hardware-software implementation of biometric identification systems based on face recognition, the relevant market is very promising — according to Bloomberg estimates its volume will grow to 7.76 billion U.S. dollars by 2022. In Moscow Technical University of Communications and Informatics (MTUCI) at the Department of Intelligent Systems in Control and Automation (ISCA) in the framework of scientific grant 3-2/2019-2-B the development of a prototype of hardware-software complex for biometric identification (HSC BI) with the use of modern methods of computer vision and neural network methods of face recognition with the possibility of subsequent integration into the security system of the university is underway. The article deals with the subsystems of face detection, file manager and server database included in the projected HSC BI.

Keywords: biometric identification, face recognition, neural network recognition, hardware-software complex, Viola-Jones method, centroid tracking method, Haar features, hardware-software architecture.

References

1. Face recognition technology – a new era in video analytics, video surveillance and access control systems. Intems URL: https://securityrussia.com/blog/face-recognition.html (date of address: 30.10.2020).
2. Face recognition. DATA-systems URL: https://www.hardbroker.ru/pages/recognition (date of address: 30.01.2020).
3. Face recognition system for the 2018 FIFA World Cup helped to detain more than 180 people. DATA-SYSTEM URL: https://www.vedomosti.ru/politics/news/2018/07/26/776624-sistema-raspoznavaniya-na-chm-2018 (contact date: 30.01.2020).
4. A facial recognition system will be introduced in Moscow. New newspaper URL: https://www.novayagazeta.ru/news/2019/09/06/155035-v-moskve-vnedryat-sistemu-raspoznavaniya-lits-na-massovyh-meropriyatiyah (date of address: 30.01.2020).
5. Facial Recognition Market worth $7.0 billion by 2024. Markets and Markets URL: https://www.marketsandmarkets.com/PressReleases/facial-recognition.asp (circulation date: 30.01.2020).
6. Maximenko V.N., Voloshina T.S. (2018). Facial recognition system analysis by the neural network algorithm. Economics and quality of communication systems. No. 4. (in Russian)
7. Ivan’ko D.V. (2016). Facial recognition system modeling with mnemonic description. Computer tools in education. (in Russian)
8. MEGVII-Your AIoT Solutions Expert URL: https://www.megvii.com/en/ (address date: 30.01.2020).
9. VisionLabs URL: https://visionlabs.ai/ru/ (date of address: 30.01.2020).
10. NTechLab URL: https://ntechlab.ru/ (access date: 30.01.2020).
11. Facial recognition: top 7 trends (tech, vendors, markets, use cases and latest news). Gemalto URL: https://www.gemalto.com/govt/biometrics/facial-recognition (access date: 30.01.2020).
12. Word. Video surveillance systems, facial recognition, photofixation of traffic violations, audio registration URL: https://vocord.ru/ (date of address: 30.01.2020).
13. Tatarenkov D.A. (2015). Analysis of the face detection methods on the image. Young scientist. No. 4.
14. Neetu Saini, Sukhwinder Kaur, Hari Singh. (2013). A Review: Face Detection Methods And Algorithms. International Journal of Engineering Research & Technology. No. 6.
15. P. Viola and M.J. Jones. (2001). Rapid Object Detection using a Boosted Cascade of Simple Features. Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR 2001).
16. P. Viola and M.J. Jones. (2004). Robust real-time face detection. International Journal of Computer Vision, vol. 57, no. 2, pp. 137-154.
17. Fransis Faux, Franck Luthon. (2012). Theory of evidence for face detection and tracking. International Journal of Approximate Reasoning. No. 53.
18. Xin Zhang, Thomas Gonnot, Jafar Saniie. (2017). Real-Time Face Detection and Recognition in Complex Background. Journal of Signal and Information Processing. No. 8.
19. Yue Zhou, Hai Tao. (2003). A Background Layer Model for Object Tracking through Occlusion. Proceedings of the Ninth IEEE International Conference on Computer Vision.
20. E.V. Zaitseva, A.L. Stepanova (2013). Classification of modern methods of object tracking and nteligent video surveillance systems. Mountain information-analytical bulletin (scientific and technical journal).
21. V.I. Voronov, L.I. Voronova, A.D. Bykov, I.A. Zharov. (2019). Software Complex of Biometric Identification Based on Neural Network Face Recognition. International Conference «Quality Management, Transport and Information Security, Information Technologies» (IT&QM&IS).
22. OpenCV URL: https://opencv.org/ (accessed on 15.09.2019).

Information about authors:
Vyacheslav I. Voronov, docent, ISCA, Cand. of Sc, Moscow Technical University of Communications and Informatics, Moscow, Russia
Alexey D. Bykov, graduate student, Moscow Technical University of Communications and Informatics, Moscow, Russia
Lilia I. Voronova, Head of the Department of ISCA, Full Professor, Doctor of Sc., Moscow Technical University of Communications and Informatics, Moscow, Russia