Issue |
E3S Web Conf.
Volume 601, 2025
The 3rd International Conference on Energy and Green Computing (ICEGC’2024)
|
|
---|---|---|
Article Number | 00109 | |
Number of page(s) | 14 | |
DOI | https://doi.org/10.1051/e3sconf/202560100109 | |
Published online | 16 January 2025 |
Advanced Facial Recognition Systems for Real-Time Embedded Applications
1 MMCS Team, EST Meknes, Moulay Ismail University, Meknes, Morocco
2 Faculty of Sciences Meknes, Moulay Ismail University, Meknes, Morocco
3 S.A.R.S Team, ENSA of Safi, UCA University, Marrakech, Morocco
4 Faculty of Science Dhar El Mahraz, Sidi Mohamed Ben Abdellah University, Fes Morocco
This article explores several classical techniques of facial recognition, assessing their suitability for real-time embedded systems such as digital cameras. It also includes a thorough discussion on the training requirements for various facial recognition methods. Addressing mounting concerns in security and surveillance, this project aims to develop an advanced facial recognition system using a 2D detection approach. Leveraging the Intel RealSense 415 camera connected to a Raspberry Pi 3. An introduction to Haar Cascading models is provided, highlighting their advantages, particularly their ability to ensure acceptable levels of accuracy for facial recognition in unseen image collections. Lastly, the article offers a detailed description and implementation of a functional platform, accompanied by preliminary results.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.