FACE RECOGNITION-BASED ATTENDANCE SYSTEM USING EIGENFACE AND SUPPORT VECTOR MACHINE ALGORITHMS

AMRULLAH, AZHAR MALIK (2025) FACE RECOGNITION-BASED ATTENDANCE SYSTEM USING EIGENFACE AND SUPPORT VECTOR MACHINE ALGORITHMS. Tugas Akhir thesis, Informatics.

Text 5190411535_AZHARMALIKAMRULLAH_ABSTRAK.pdf Download (65kB)

Abstract

Many university students maintain good attendance records without being marked absent, which has led to instances of fraudulent attendance practices. In QR code–based attendance systems, some students exploit the system by asking peers to submit the unique lecturer-provided link or by allowing others to log in on their behalf without proper authentication. To address this issue, this study proposes a facial recognition–based attendance application leveraging the Eigenface algorithm for feature extraction and the Support Vector Machine (SVM) for classification to ensure that the student logging attendance is the verified account owner. The system utilizes facial image datasets from 11 students, each comprising 20 training images and 5 testing images. The datasets vary in facial structure, lighting intensity, facial expressions, and background environments. Experimental results across the 11 classes demonstrated an accuracy rate of 96.36% under optimal lighting conditions, as reported in the classification summary. However, the system is highly sensitive to variations in lighting and facial positioning during real-time webcam capture, often resulting in fluctuating predictions. Furthermore, similar backgrounds among datasets sometimes hinder accurate face recognition. For enhanced system performance, future development should consider expanding the dataset, standardizing lighting and backgrounds, or incorporating training data from diverse lighting scenarios to improve both data recording and real-time testing. Keywords: System, Attendance, Face Recognition, Webcam, Eigenface, Support Vector Machine

Item Type:	Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects:	T Technology > T Technology (General)
Divisions:	Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User:	Kaprodi S1 Informatika UTY
Date Deposited:	24 Jul 2025 04:03
Last Modified:	24 Jul 2025 04:03
URI:	http://eprints.uty.ac.id/id/eprint/18355

Actions (login required)

View Item