Research Article
A Comparative Analysis of Facial Recognition Techniques Using Machine Learning Algorithms
@INPROCEEDINGS{10.4108/eai.28-4-2025.2357974, author={Suruchi Dhawan and Nivin Samuel and Swati Swati and Nicky Choudhary and Jyoti Kumari and Isha Singh}, title={A Comparative Analysis of Facial Recognition Techniques Using Machine Learning Algorithms}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part II}, publisher={EAI}, proceedings_a={ICITSM PART II}, year={2025}, month={10}, keywords={face recognition deep learning attendance system manual attendance system automated attendance system local binary pattern histogram of oriented gradients scale invariant feature transform convolutional neural network support vector machine}, doi={10.4108/eai.28-4-2025.2357974} }- Suruchi Dhawan
Nivin Samuel
Swati Swati
Nicky Choudhary
Jyoti Kumari
Isha Singh
Year: 2025
A Comparative Analysis of Facial Recognition Techniques Using Machine Learning Algorithms
ICITSM PART II
EAI
DOI: 10.4108/eai.28-4-2025.2357974
Abstract
Face recognition is a highly effective application of image processing, playing a pivotal role in technological advancements. This study deals with the development of an automated attendance system using facial recognition technology to enhance authentication in student attendance management. Traditional methods, such as manual roll-call and record-keeping, are often inefficient, prone to errors, and susceptible to manipulation. Even conventional biometric systems face challenges, including the possibility of proxy attendance. To address these issues, this study explores a facial recognition-based approach that integrates biometric data with high- definition monitoring and advanced computational techniques. The system automates attendance tracking, ensuring accuracy and reducing human intervention. Attendance records are automatically generated and stored in Excel format for easy access and analysis. The system's performance is evaluated under different conditions, including variations in lighting, head movements, and student-camera distance. Experimental results demonstrate high accuracy and efficiency, establishing the system as a reliable, cost-effective, and easily deployable solution for classroom attendance management.
