Proceedings of the International Conference on Cross- Disciplinary Academic Research 2025 - Track 1 Advances in Computing, Electronics, Engineering, and Mathematics (ICAR-T1 2025)

<Previous Article In Volume
Next Article In Volume>

A Comparative Experimental Evaluation of YOLOv5, YOLOv7, and YOLOv8 for Object Detection

Authors
Airuddin Ahmad1, *, Haw Ying Song2
1Universiti Poly-Tech Malaysia, Jalan 6/91, Taman Shamelin Perkasa, 56100 Cheras, Kuala Lumpur, Malaysia
2Universiti Terbuka Malaysia, No 559, Jalan Langgar 05000 Alor Setar, Kedah, Malaysia
*Corresponding author. Email: airuddin@uptm.edu.my
Corresponding Author
Airuddin Ahmad
Available Online 28 April 2026.
DOI
10.2991/978-94-6239-636-4_2How to use a DOI?
Keywords
YOLOv5; YOLOv7; YOLOv8; Comparative Study
Abstract

The purpose of this comparative study is to investigate the differences between the YOLOv5, YOLOv7, and YOLOv8 when detecting specific objects. Therefore, this study will focus on examining the precision performance, recall capabilities, IoU performance, and the balance between precision and recall of YOLOv5, YOLOv7, and YOLOv8 compared under systematic evaluation. This study was conducted by employing an experimental design. The experimental setup will be employed by using Google Colab as the platform, and the Google Colab Runtime type is Python 3 and T4 GPU. Additionally, the dataset is selected from the Roboflow Public Dataset, a total of 2781 images were selected. The results indicate that YOLOv5 is better performing in precision, recall, and the balance between precision and recall. Additionally, YOLOv8 is better in the value of Intersection over Union (IoU) performance. This study contributes insights that can have implications for future research, the education sector, institutions, technical optimization, and industrial development. Future researchers can use this study as a reference to delve into more diverse and in-depth studies on object detection algorithms.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Cross- Disciplinary Academic Research 2025 - Track 1 Advances in Computing, Electronics, Engineering, and Mathematics (ICAR-T1 2025)
Series
Advances in Engineering Research
Publication Date
28 April 2026
ISBN
978-94-6239-636-4
ISSN
2352-5401
DOI
10.2991/978-94-6239-636-4_2How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Airuddin Ahmad
AU  - Haw Ying Song
PY  - 2026
DA  - 2026/04/28
TI  - A Comparative Experimental Evaluation of YOLOv5, YOLOv7, and YOLOv8 for Object Detection
BT  - Proceedings of the International Conference on Cross- Disciplinary Academic Research 2025 - Track 1 Advances in Computing, Electronics, Engineering, and Mathematics (ICAR-T1 2025)
PB  - Atlantis Press
SP  - 4
EP  - 13
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-636-4_2
DO  - 10.2991/978-94-6239-636-4_2
ID  - Ahmad2026
ER  -