DOI : https://doi.org/10.18517/ijaseit.15.2.20495

The Effect of the Number of Classes on the Values Resulting from Evaluation Metrics in the YOLOv5 Model

Esi Putri Silmina (1), Tikaridha Hardiani (2), Silvi Lailatul Mahfida (3)
(1) Information Technology Study Program, Universitas ‘Aisyiyah Yogyakarta, Sleman, D.I. Yogyakarta, Indonesia
(2) Information Technology Study Program, Universitas ‘Aisyiyah Yogyakarta, Sleman, D.I. Yogyakarta, Indonesia
(3) Nutrition Study Program, Universitas ‘Aisyiyah Yogyakarta, Sleman, D.I. Yogyakarta, Indonesia
Fulltext View | Download
How to cite (IJASEIT) :
[1]
E. Putri Silmina, T. Hardiani, and S. Lailatul Mahfida, “The Effect of the Number of Classes on the Values Resulting from Evaluation Metrics in the YOLOv5 Model”, Int. J. Adv. Sci. Eng. Inf. Technol., vol. 15, no. 2, pp. 419–425, Apr. 2025.
Citation Format :
Object detection is an essential field in computer vision. Building an object detection model requires specific categories during training: classes. This study aims to analyze the effect of the number of classes on the evaluation metrics obtained from detection model training. The dataset consists of ten classes, each containing one hundred images of size 416 x 416 pixels.  The detection model is trained using the YOLOv5 model with one hundred epochs and a batch size of 16. Testing is done five times with the number of classes increasing gradually, namely two classes, four classes, six classes, eight classes, and ten classes. The test results in evaluation metrics, namely precision, recall, [email protected], [email protected]:0.95, and training time, were analyzed and compared. The analysis shows that the number of classes significantly affects the accuracy of the evaluation metrics. Training a model with eight classes gives the best accuracy results with a precision of 75.5%, recall of 62.5%, [email protected] of 71.2%, and [email protected]:0.95 of 35.5%. Meanwhile, training the model with two classes produced the lowest results, and training with 10 classes decreased compared to eight classes. A non-linear analysis relationship was also observed, as using ten classes slightly reduced the matrix value while maintaining efficiency in training time. This concludes that increasing the number of classes does not necessarily improve accuracy, and the optimal class configuration needs further consideration. These findings highlight important considerations for optimizing object detection models using YOLOv5 and contribute to future development.

J. Kaur and W. Singh, A systematic review of object detection from images using deep learning, vol. 83, no. 4. Springer US, 2024. doi:10.1007/s11042-023-15981-y.

J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You only look once: Unified real-time object detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, 2016.

K. Zhao, "Enhancing the Performance and Accuracy in Real-Time Football and Player Detection Using Upgraded YOLOv5 Architecture," Int. J. Comput. Intell. Syst., vol. 17, no. 1, 2024, doi:10.1007/s44196-024-00565-x.

A. J. Azmawi, W. N. Mohd-Isa, and A. A. A. Rahman, "Telecommunication Fiber Box Detection Using YOLO in Urban Environment," Int. J. Adv. Sci. Eng. Inf. Technol., vol. 13, no. 6, pp. 2136-2144, 2023, doi: 10.18517/ijaseit.13.6.19027.

A. Balasundaram, A. Mohanty, A. Shaik, K. Pradeep, K. P. Vijayakumar, and M. S. Kavitha, "Zero-DCE++ Inspired Object Detection in Less Illuminated Environment Using Improved YOLOv5," Comput. Mater. Contin., vol. 77, no. 3, pp. 2751-2769, 2023, doi: 10.32604/cmc.2023.044374.

J. Kaur and W. Singh, "Tools, techniques, datasets and application areas for object detection in an image: a review," Multimed. Tools Appl., vol. 81, no. 27, pp. 38297-38351, 2022, doi: 10.1007/s11042-022-13153-y.

U. Sirisha, S. P. Praveen, P. N. Srinivasu, P. Barsocchi, and A. K. Bhoi, "Statistical Analysis of Design Aspects of Various YOLO-Based Deep Learning Models for Object Detection," Int. J. Comput. Intell. Syst., vol. 16, no. 1, pp. 1-29, 2023, doi: 10.1007/s44196-023-00302-w.

S. S. Debnath, R. K. Verma, and P. Mahudapathi, Real-Time Object Detection Using YOLOv5, vol. 405 SIST. Springer Nature Singapore, 2024. doi: 10.1007/978-981-97-6222-4_38.

V. A. Kich et al., "Precision and Adaptability of YOLOv5 and YOLOv8 in Dynamic Robotic Environments," in 2024 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE International Conference on Robotics, Automation and Mechatronics (RAM), 2024, pp. 514-519. doi: 10.1109/CIS-RAM61939.2024.10673292.

J. Wang et al., "Research on Tea Trees Germination Density Detection Based on Improved YOLOv5," Forests, vol. 13, no. 12, 2022, doi:10.3390/f13122091.

J. H. Lee and K. S. Song, "Comparison and Analysis of CNN Models to Improve a Facial Emotion Classification Accuracy for Koreans and East Asians," Int. J. Adv. Sci. Eng. Inf. Technol., vol. 14, no. 3, pp. 811-817, 2024, doi: 10.18517/ijaseit.14.3.18078.

T. Mahendrakar et al., "Performance Study of YOLOv5 and Faster R-CNN for Autonomous Navigation around Non-Cooperative Targets," IEEE Aerosp. Conf. Proc., vol. 2022-March, pp. 1-12, 2022, doi:10.1109/aero53065.2022.9843537.

R. Han, Y. Zheng, R. Tian, and L. Shu, "An image dataset for analyzing tea picking behavior in tea plantations," no. January, pp. 1-8, 2025, doi: 10.3389/fpls.2024.1473558.

A. Vijayakumar and S. Vairavasundaram, YOLO-based Object Detection Models: A Review and its Applications, no. 0123456789. Springer US, 2024. doi: 10.1007/s11042-024-18872-y.

T. Diwan, G. Anirudh, and J. V. Tembhurne, "Object detection using YOLO: challenges, architectural successors, datasets and applications," Multimed. Tools Appl., vol. 82, no. 6, pp. 9243-9275, 2023, doi: 10.1007/s11042-022-13644-y.

J. Lee and K. il Hwang, "YOLO with adaptive frame control for real-time object detection applications," Multimed. Tools Appl., vol. 81, no. 25, pp. 36375-36396, 2022, doi: 10.1007/s11042-021-11480-0.

J. Terven, D. M. Córdova-Esparza, and J. A. Romero-González, "A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS," Mach. Learn. Knowl. Extr., vol. 5, no. 4, pp. 1680-1716, 2023, doi: 10.3390/make5040083.

F. Prinzi, M. Insalaco, A. Orlando, S. Gaglio, and S. Vitabile, "A Yolo-Based Model for Breast Cancer Detection in Mammograms," Cognit. Comput., vol. 16, no. 1, pp. 107-120, 2024, doi: 10.1007/s12559-023-10189-6.

J. Zhong, Q. Cheng, X. Hu, and Z. Liu, "YOLO Adaptive Developments in Complex Natural Environments for Tiny Object Detection," Electron., vol. 13, no. 13, 2024, doi:10.3390/electronics13132525.

Z. Yu, H. Huang, W. Chen, Y. Su, Y. Liu, and X. Wang, "YOLO-FaceV2: A scale and occlusion aware face detector," Pattern Recognit., vol. 155, p. 110714, 2024, doi:10.1016/j.patcog.2024.110714.

S. P. Yadav, M. Jindal, P. Rani, V. H. C. de Albuquerque, C. dos Santos Nascimento, and M. Kumar, "An improved deep learning-based optimal object detection system from images," Multimed. Tools Appl., vol. 83, no. 10, pp. 30045-30072, 2024, doi: 10.1007/s11042-023-16736-5.

F. Rashidi Ranjbar and A. Zamanifar, "Autonomous dental treatment planning on panoramic x-ray using deep learning based object detection algorithm," Multimed. Tools Appl., vol. 83, no. 14, pp. 42999-43033, 2024, doi: 10.1007/s11042-023-17048-4.

A. Bal, M. Das, and S. M. Satapathy, "YOLO as a Region Proposal Network for Diagnosing Breast Cancer," 2021 Grace Hopper Celebr. India, GHCI 2021, pp. 1-6, 2021, doi:10.1109/ghci50508.2021.9513988.

A. Karaman et al., "Robust real-time polyp detection system design based on YOLO algorithms by optimizing activation functions and hyper-parameters with artificial bee colony (ABC)," Expert Syst. Appl., vol. 221, p. 119741, 2023, doi: 10.1016/j.eswa.2023.119741.

R. Kaur and S. Singh, "A comprehensive review of object detection with deep learning," Digit. Signal Process., vol. 132, p. 103812, 2023, doi: 10.1016/j.dsp.2022.103812.

X. Wu, D. Sahoo, and S. C. H. Hoi, "Recent advances in deep learning for object detection," Neurocomputing, vol. 396, pp. 39-64, 2020, doi:10.1016/j.neucom.2020.01.085.

M. Hussain, "YOLOv1 to v8: Unveiling Each Variant-A Comprehensive Review of YOLO," IEEE Access, vol. 12, no. February, pp. 42816-42833, 2024, doi:10.1109/access.2024.3378568.

R. Al Amin, M. Hasan, V. Wiese, and R. Obermaisser, "FPGA-Based Real-Time Object Detection and Classification System Using YOLO for Edge Computing," IEEE Access, vol. 12, no. May, pp. 73268-73278, 2024, doi: 10.1109/ACCESS.2024.3404623.

Z. Zou, K. Chen, Z. Shi, Y. Guo, and J. Ye, "Object Detection in 20 Years: A Survey," Proc. IEEE, vol. 111, no. 3, pp. 257-276, 2023, doi:10.1109/JPROC.2023.3238524.

R. Sapkota et al., "YOLOv10 to Its Genesis: A Decadal and Comprehensive Review of The You Only Look Once Series," 2024, arXiv: 2406.19407, doi: 10.2139/ssrn.4874098

X. Zhai, Z. Huang, T. Li, H. Liu, and S. Wang, "YOLO-Drone: An Optimized YOLOv8 Network for Tiny UAV Object Detection," Electron., vol. 12, no. 17, 2023, doi: 10.3390/electronics12173664.

J. Miao et al., "YOLO-VSF: An Improved YOLO Model by Incorporating Attention Mechanism for Object Detection in Traffic Scenes," J. Shanghai Jiaotong Univ., 2024, doi: 10.1007/s12204-024-2751-y.

X. Han, J. Chang, and K. Wang, "Real-time object detection based on YOLO-v2 for tiny vehicle objects," Procedia Comput. Sci., vol. 183, pp. 61-72, 2021, doi: 10.1016/j.procs.2021.02.031.

C. Zhao et al., "AC-YOLO: Multi-category and high-precision detection model for stored grain pests based on integrated multiple attention mechanisms," Expert Syst. Appl., vol. 255, p. 124659, 2024, doi: 10.1016/j.eswa.2024.124659.

X. Cao, J. Wu, J. Chen, and Z. Li, "Complex Scenes Fire Object Detection Based on Feature Fusion and Channel Attention," Arab. J. Sci. Eng., 2024, doi: 10.1007/s13369-024-09471-y.

C. Santos, M. Aguiar, D. Welfer, and B. Belloni, "A New Approach for Detecting Fundus Lesions Using Image Processing and Deep Neural Network Architecture Based on YOLO Model," Sensors, vol. 22, no. 17, 2022, doi: 10.3390/s22176441.

J. Ye, Z. Yuan, C. Qian, and X. Li, "CAA-YOLO: Combined-Attention-Augmented YOLO for Infrared Ocean Ships Detection," Sensors, vol. 22, no. 10, pp. 1-23, 2022, doi: 10.3390/s22103782.

L. Zhao, T. Tohti, and A. Hamdulla, "BDC-YOLOv5: a helmet detection model employs improved YOLOv5," Signal, Image Video Process., vol. 17, no. 8, pp. 4435-4445, 2023, doi: 10.1007/s11760-023-02677-x.

L. Zhang, J. Li, and F. Zhang, "An Efficient Forest Fire Target Detection Model Based on Improved YOLOv5," Fire, vol. 6, no. 8, 2023, doi: 10.3390/fire6080291.

H. Liu, X. Duan, H. Lou, J. Gu, H. Chen, and L. Bi, "Improved GBS-YOLOv5 algorithm based on YOLOv5 applied to UAV intelligent traffic," Sci. Rep., vol. 13, no. 1, pp. 1-12, 2023, doi: 10.1038/s41598-023-36781-2.

N. T. Nguyen, Q. Tran, C. H. Dao, D. A. Nguyen, and D. H. Tran, "Automatic Detection of Personal Protective Equipment in Construction Sites Using Metaheuristic Optimized YOLOv5," Arab. J. Sci. Eng., vol. 49, no. 10, pp. 13519-13537, 2024, doi:10.1007/s13369-023-08700-0.

S. Li, S. Liu, Z. Cai, Y. Liu, G. Chen, and G. Tu, "TC-YOLOv5: rapid detection of floating debris on raspberry Pi 4B," J. Real-Time Image Process., vol. 20, no. 2, pp. 1-13, 2023, doi: 10.1007/s11554-023-01265-z.

H. Wang, Y. Jin, H. Ke, and X. Zhang, "DDH-YOLOv5: improved YOLOv5 based on Double IoU-aware Decoupled Head for object detection," J. Real-Time Image Process., vol. 19, no. 6, pp. 1023-1033, 2022, doi: 10.1007/s11554-022-01241-z.

W. Sun, H. Li, Q. Liang, X. Zou, M. Chen, and Y. Wang, On data efficiency of univariate time series anomaly detection models, vol. 11, no. 1. Springer International Publishing, 2024. doi: 10.1186/s40537-024-00940-7.

Z. Hammoudeh and D. Lowd, Training data influence analysis and estimation: a survey, vol. 113, no. 5. Springer US, 2024. doi:10.1007/s10994-023-06495-7.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).