FACIAL RECOGNITION-BASED IDENTITY VERIFICATION AND DETECTION SYSTEM

N. Karpiuk, Halyna Klym, O. Stepanov, I. Vasylchyshyn

Abstract


This scientific investigation is dedicated to an in-depth exploration and comprehensive evaluation of the Haar cascade classifier method as an essential component of facial recognition technology. In addition to its rigorous analysis, this paper substantiates the rationale behind selecting this particular algorithm and offers a detailed account of the system's implementation process, shedding light on the intricacies of the experimental setup employed for our study. The crafted facial recognition system underwent rigorous testing using a diverse dataset of facial photographs. This dataset included a broad spectrum of images captured at varying distances from the camera, under diverse lighting conditions, and encompassing various facial orientations within the camera's field of view. Subsequent to the extensive testing phase, a meticulous analysis of the test results was meticulously conducted. These results provided valuable insights into the system's strengths and weaknesses, highlighting the significance of certain factors in achieving optimal accuracy in facial recognition technology. The in-depth evaluation allowed us to draw robust conclusions regarding the critical considerations essential for the effective design and deployment of facial recognition systems aimed at attaining exceptionally high levels of precision and reliability. By identifying these factors, our research contributes significantly to the advancement of facial recognition technology, paving the way for more accurate and dependable systems in various applications.

Key words: system, recognition, device, face tracking. algorithm, Haar classifiers.


Full Text:

PDF

References


  1. Tian Y. Artificial intelligence image recognition method based on convolutional neural network algorithm // IEEE Access. – 2020. – Vol. 8. – P. 125731-125744.
  2. Liyakat, K. Development of Pose Invariant Face Recognition Method Based on Pca and Artificial Neural Network / K. K. S.Liyakat, V. A Mane, K. P .Paradeshi, D. B. Kadam, & K. K. Pandyaji // Journal of Algebraic Statistics. – 2022. –Vol. 13(3). –P. 3676-3684.
  3. Kumar A. Face detection techniques: a review / A. Kumar, A. Kaur, & M. Kumar, // Artificial Intelligence Review/ – 2019. – Vol. 52. – P. 927-948.
  4. Singh Bhadauriya S. “Real-Time Face Detection and Face Recognition: Study of Approaches” / S. Singh Bhadauriya, S. Kushwaha, S. Meena // Lecture Notes in Networks and Systems. Singapore. – 2023.– P. 297–308.
  5. Phuc L. T. H. “Applying the Haar-cascade Algorithm for detecting safety equipment in safety management systems for multiple working environments,” / L. T. H. Phuc, H. Jeon, N. T. N. Truong, J. J. Hak // Electronics. – 2019. – Vol. 8(10).– P 1079.
  6. Andrejevic M. “Facial recognition technology in schools: Critical questions and concerns,” / M. Andrejevic, N. Selwyn // Learning, Media and Technology.– 2020. – Vol. 45(2).– P. 115-128.
  7. Lai X. “Has facial recognition technology been misused? A public perception model of facial recognition scenarios” / X. Lai, & P. L. P. Rau // Computers in Human Behavior. – 2021. – Vol. 124. – P. 106894.
  8. Budiman R. A. M. “Localization of white blood cell images using Haar cascade classifiers,” / R. A. M Budiman, B. Achmad, A. Arif, L. Zharif // 1st International Conference on Biomedical Engineering (IBIOMED).–2016.–P. 1-5.
  9. Marchesotti L. Dual camera system for face detection in unconstrained environments / L. Marchesotti, L. Marcenaro, & C. Regazzoni // In Proceedings 2003 International Conference on Image Processing IEEE.–2003.–Vol.1 (Cat. No. 03CH37429).– P. I-681.
  10. Balasubramanian M. Deep transfer learning based real time face mask detection system with computer vision / M. Balasubramanian, K. Ramyadevi, & R. Geetha // Multimedia Tools and Applications.–2023.–P. 1-20.
  11. Hashim S. Face detection by using Haar Cascade Classifier / S. Hashim, & P. Mccullagh // Wasit Journal of Computer and Mathematics Science.–2023.–Vol. 2(1).–P. 1-8.
  12. Singh G. Face detection and recognition system using digital image processing / G. Singh, & A. K. Goel // In 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA). IEEE.–2020. –P. 348-352.
  13. Aliyu I. “Comparative Study of Eigenface and Fisherface Algorithms Based on OpenCV and Sci-kit Libraries Implementations” / I. Aliyu, M. Ali Bomoi, M. A Maishanu // International Journal of Information Engineering and Electronic Business.– 2022. – Vol. 14(3). –P. 30–40.
  14. Mulyono I. U. W. “Performance analysis of face recognition using eigenface approach,” / I. U. W. Mulyono, A. Susanto, E. H. Rachmawanto, A. Fahmi // International Seminar on Application for Technology of Information and Communication. –2019.– P. 1-5.




DOI: http://dx.doi.org/10.30970/eli.23.3

Refbacks

  • There are currently no refbacks.