Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63098
Volume:
10 |
5 |
May 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Engineering
Vidya Niketan College of Engineering, Bota
Computer Engineering
Vidya Niketan College of Engineering, Bota
Computer Engineering
Vidya Niketan College of Engineering, Bota
Computer Engineering
Vidya Niketan College of Engineering, Bota
Facial recognition systems are widely used in modern applications such as security systems, smart attendance, access control, and surveillance monitoring. However, many traditional systems face difficulties in recognizing multiple faces accurately in real-time environments due to variations in lighting, face angles, facial expressions, and image quality. To overcome these challenges, this project presents a real-time multiple face recognition system using Convolutional Neural Networks (CNN) integrated with Gravitational Search Optimization (GSO) for optimized feature selection and improved recognition performance. The proposed system is developed using Python, OpenCV, OpenVINO, and Flask framework. The system captures facial data through a live camera feed, detects and recognizes multiple faces simultaneously, and compares them with stored face encodings in the database. CNN-based models are used for face detection and feature extraction, while GSO is applied to optimize important facial features from the extracted embeddings to improve recognition accuracy and reduce unnecessary feature complexity. The system also provides a user-friendly web interface for adding new faces, managing the face database, and performing real-time face recognition. Experimental results show that the proposed system performs efficiently in real-time conditions and provides accurate recognition for multiple individuals appearing simultaneously in the camera feed. The developed system can be effectively used in smart surveillance, attendance management, and security-based applications.
KEYWORDS
In this project, a real-time multiple face recognition system using CNN and Gravitational Search Optimization (GSO) was successfully developed. The system is capable of detecting and recognizing multiple persons simultaneously from a live camera feed using OpenVINO, OpenCV, Flask, and Python. The use of CNN models improved facial feature extraction, while GSO helped optimize important facial features for better recognition accuracy and performance. The system also provides a simple web interface for face registration, database management, and real-time testing. The developed system can be effectively used in applications such as smart attendance, surveillance, and security systems. Future improvements can include multi-camera support and cloud-based database integration.
[1] R. H. R. Al-Abboodi and A. A. Al-Ani, “A Novel Technique for Facial Recognition Based on the GSO-CNN Deep Learning Algorithm,” Journal of Electrical and Computer Engineering, vol. 2024, pp. 1–21, 2024. [2] Z. Khan, A. I. Umar, S. H. Shirazi, M. Shahzad, and M. Assam, “Face Recognition via Multi-Level 3D-GAN Colorization,” IEEE Access, vol. 10, pp. 12504–12516, 2022. [3] B. M. Nguyen, T. Tran, T. Nguyen, and G. Nguyen, “Hybridization of Galactic Swarm and Evolution Whale Optimization for Global Search Problems,” IEEE Access, vol. 8, pp. 126861–126872, 2020. [4] H. B. Kim, N. Choi, H. J. Kwon, and H. Kim, “Surveillance System for Real-Time High-Precision Recognition of Criminal Faces from Wild Videos,” IEEE Access, vol. 11, pp. 71524–71535, 2023. [5] A. Rahim, Y. Zhong, T. Ahmad, S. Ahmad, P. Pławiak, and M. Hammad, “Enhancing Smart Home Security: Anomaly Detection and Face Recognition in Smart Home IoT Devices Using Logit-Boosted CNN Models,” Sensors, vol. 23, no. 15, pp. 6979, 2023. [6] K. Chen, S. Chen, S. Zhang, and H. Zhao, “Automatic Modulation Recognition of Radar Signals Based on Histogram of Oriented Gradient via Improved Principal Component Analysis,” Signal, Image and Video Processing, vol. 17, no. 6, pp. 3053–3061, 2023.
Publication Date
6/14/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
9
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...