Currently, the biometric identification methods based on the unique physical and behavioral characteristics of a person are widely used in control systems and access to information. The face recognition system permits to automate an access to protected objects using computer vision. An important role in such a system plays the creation of a database for persons with an access to the object. Here, the creation of the database of persons with an access to the working object plays an important role in such system. In this work the principal component method for implementing the face recognition process has been proposed. The method permits to reduce the dimensionality of the data with the loss of the least amount of important information. The Viola-Jones algorithm is used to detect faces, to create a database of faces and to test the recognition results. For calculating the distances between the test images and the database images the Euclidean distance metric has been used. It has been shown that the preliminary processing of the data can improve the recognition results.
1. Bakshi U., Singhal R. A survey on face detection methods and feature extraction techniques of face recognition // International Journal of Emerging Trends & Technology in Computer Science (IJETTCS). 2014. No. 3. Vol. 3. P. 233–237.
2. Barnouti, Nawaf Hazim. Improve face recognition rate using different image pre-processing techniques // American Journal of Engineering Research (AJER). 2016. No. 5. Vol.4. P. 46–53.
3. Cross-race effect. URL: https://ru.qwe.wiki/wiki/Cross-race_effect (дата обращения: 25.03.2020).
4. Viola P., Jones M. Robust real-time face detection // International Journal of Сomputer Vision. 2004. No. 57. P. 139–145.
5. Viola P., Jones M. Robust real-time object detection // 2nd International Workshop on Statistical and Computational Theories of Vision – Modelling, Learning, Computing, and Sampling (Vancouver, Canada, July 13, 2001). 2001. P. 4–14.
6. Вай Ян Мин, Лисовец Ю.П, Романова Е.Л, Тхет Наинг Вин. Применение статистической обработки данных для повышения эффективности распознавании лиц при использовании метода главных компонент // Электронные информационные системы. 2019. № 2 (21). C. 35–37.
7. Anand Singh, Erarica Mehra, Saundarya Dorle. Face recognition using principal component analysis // International Journal of Advanced Technology in Engineering and Science. 2016. Vol. 4. Iss. 03. P. 611–614.
8. Вай Ян Мин. Моделирование контрольно-пропускного пункта для решения задачи обнаружения и идентификации лиц // 25-я Всероссийская межвузовская науч.-техн. конф. студентов и аспирантов
«Микроэлектроника и информатика – 2018». M.: МИЭТ, 2018. С. 115.
9. Вай Ян Мин, Лисовец Ю.П., Романова Е.Л., Зо Льин У. Алгоритмы идентификации человека на входе автоматизированного контрольно-пропускного пункта с использованием метода главных компонент // Электронные информационные системы. 2020. № 1 (24). С. 41–43.