Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Applied Artificial Intelligence and Robotics (IJAIC)
Heri Maulana
Jurusan Teknologi Informasi dan Komputer, Politeknik Negeri lhokseumawe

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
An Intelligent Student Attendance System Based on Facial Image Recognition Using YOLOv5: A Case Study at Politeknik Negeri Lhokseumawe Heri Maulana; Azhar Azhar; Rahmad Hidayat; Eni Mawardhaningrum
International Journal of Applied Artificial Intelligence and Robotics Vol 2 No 1 (March 2026)
Publisher : PT. Literasi Teknologi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67745/ijaic.v2i1.15

Abstract

You Only Look Once (YOLO) is an effective deep learning method for real-time object detection. This method is applied to build an accurate, fast facial recognition model, with a case study on an attendance system based on facial images at the Lhokseumawe State Polytechnic. The main objective is to implement and evaluate the YOLOv5s model's performance on the attendance system using facial images with high accuracy. The research process includes collecting facial image datasets from 40 subjects with various viewing angles to train the YOLOv5s model. This model is specifically configured to detect one class of objects, namely faces, and then integrated into the system to function as the main face detector. Model performance is evaluated quantitatively using a confusion matrix to measure key metrics such as accuracy, precision, recall, and F1 score. The evaluation results show that the developed YOLOv5s model has excellent performance. This model achieved 90% accuracy, with a precision and recall of 92%. The balanced F1-score value (92%) proves that the YOLOv5s method has a high level of accuracy for detecting faces. The high-performance metrics confirm that this method is the right solution for building an attendance system based on accurate facial images.
Co-Authors Azhar Azhar Eni Mawardhaningrum Rahmad Hidayat