Enhancing Attendance Management with Facial Recognition: A Web and Mobile-Based System

Simple item page
dc.contributor.authorAjayi, Adebimpe Ruth
dc.contributor.authorOmotola, David A.
dc.contributor.authorOlanrewaju Mubarak D.
dc.contributor.authorAjayi, Mark O.
dc.contributor.authorAdebayo, Olalekan F.
dc.contributor.authorAdesina Ayodele J.
dc.date.accessioned2025-05-26T14:17:47Z
dc.date.available2025-05-26T14:17:47Z
dc.date.issued2025-03
dc.description.abstractThe development of a facial recognition-based attendance management system is presented in this study. By leveraging facial recognition technology, the system offers a reliable, efficient, and secure alternative to traditional methods such as manual roll calls and paper-based records, which are prone to errors and manipulation. The system employed an Android application to capture students' facial images, which are then processed using advanced Image Processing APIs, including OpenCV and the Python Face Recognition library, to identify and authenticate individuals. The Dlib open-source library which uses a Histogram of Oriented Gradients (HOG) and linear Support Vector Machine (SVM) was used as the face detection model. The system’s performance was evaluated using the False Acceptance Rate (FAR) and False Rejection Rate (FRR) metrics. The results indicated a FAR of 0%, ensuring the system effectively blocks illegitimate attendance entries. However, an FRR of approximately 5% was observed, highlighting challenges in accurately identifying legitimate users under varying conditions such as changes in lighting and facial expressions. Keywords— Attendance Management, False Acceptance Rate (FAR), False Rejection Rate (FRR), OpenCV
dc.identifier.urihttps://uilspace.unilorin.edu.ng/handle/123456789/16816
dc.titleEnhancing Attendance Management with Facial Recognition: A Web and Mobile-Based System

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
1295-Article Text-15090-1-10-20250430.pdf
Size:
984.9 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections