Advanced Deep Learning-Based Potato Defect Identification Leveraging YOLOv8 for Smart Agriculture

Waqas Ahmad; Aqib Mehmood; Arshad Kamal; Daud Khan; Aziz Khan; Salman Ali Khan; Mohsin Tahir; Muhammad Ayub Khan; Mubashir Zainoor; Latif Jan

Authors

Waqas Ahmad Iqra National University, Peshawar, Pakistan
Aqib Mehmood Iqra National University, Peshawar, Pakistan
Arshad Kamal Xi’an Shiyou University, China
Daud Khan Iqra National University, Peshawar, Pakistan
Aziz Khan University of Roehampton, London
Salman Ali Khan Iqra National University, Peshawar, Pakistan
Mohsin Tahir Iqra National University, Peshawar, Pakistan
Muhammad Ayub Khan Iqra National University, Peshawar, Pakistan
Mubashir Zainoor Iqra National University, Peshawar, Pakistan
Latif Jan Iqra National University, Peshawar, Pakistan

Keywords:

Computer Vision, Yolov8, Object Detection, Potato Classification, Deep Learning, Agricultural Technology, Post-Harvest Management

Abstract

This paper presents the design of an effective deep learning model to identify and rank potato defects, enabling intelligent farming and post-harvest tasks. The primary goal is to automate the quality measurement of potatoes in several categories: healthy, damaged, defective, fungal-diseased, and sprouted, with the help of an optimized YOLOv8 model. The data set on potato images was annotated and gathered in the real-world agricultural conditions in a wide variety of images. Data augmentation and transfer learning were used to train the model and enhance generalization and detection rates in different conditions. The experiment showed that the detection performance was high and it reached 95.3% training accuracy, 93.8% validation accuracy, and 92.5% test accuracy with an F1-score of 92.9. The results verify that the suggested approach plays a crucial role in detecting defects in potatoes in real time, which can be used to support comprehensive, computerized, and accurate agricultural surveillance.

References

A. M. Ayalew, A. O. Salau, B. T. Abeje, and B. Enyew, “Detection and classification of COVID-19 disease from X-ray images using convolutional neural networks and histogram of oriented gradients,” Biomed. Signal Process. Control, vol. 74, p. 103530, Apr. 2022, doi: 10.1016/J.BSPC.2022.103530.

V. Mousavi, M. Varshosaz, F. Remondino, S. Pirasteh, and J. Li, “A Two-Step Descriptor-Based Keypoint Filtering Algorithm for Robust Image Matching,” IEEE Trans. Geosci. Remote Sens., vol. 60, 2022, doi: 10.1109/TGRS.2022.3188931.

Y. Luo, J. Sa, Y. Song, H. Jiang, C. Zhang, and Z. Zhang, “Texture classification combining improved local binary pattern and threshold segmentation,” Multimed. Tools Appl., vol. 82, no. 17, pp. 25899–25916, Jul. 2023, doi: 10.1007/S11042-023-14749-8/TABLES/6.

M. Zdybal, M. Kucharczyk, and M. Wolter, “Machine learning based event reconstruction for the MUonE experiment,” Comput. Sci., vol. 25, no. 1, pp. 25–46, Feb. 2024, doi: 10.7494/csci.2024.25.1.5690.

G. Fabris, L. Scalera, and A. Gasparetto, “Playing Checkers with an Intelligent and Collaborative Robotic System,” Robot. 2024, Vol. 13, Page 4, vol. 13, no. 1, p. 4, Dec. 2023, doi: 10.3390/ROBOTICS13010004.

H. Nieto-Chaupis, “Machine learning as an advanced algorithm to solve optimization problems in physics,” Proc. 2021 5th World Conf. Smart Trends Syst. Secur. Sustain. WorldS4 2021, pp. 294–298, Jul. 2021, doi: 10.1109/WORLDS451998.2021.9514008.

H. Nieto-Chaupis, “Machine Learning of a Pair of Charged Electrically Particles Inside a Closed Volume: Electrical Oscillations as Memory and Learning of System,” Lect. Notes Networks Syst., vol. 507 LNNS, pp. 247–256, 2022, doi: 10.1007/978-3-031-10464-0_16.

A. L. dos Santos Safre, “Precision Agriculture Applications in Tart Cherries: Yield Mapping Technologies and Remote Sensing for Water Stress Estimation,” All Grad. Theses Diss. Fall 2023 to Present, Aug. 2025, doi: https://doi.org/10.26076/72fa-ec32.

C. Tan, C. Li, J. Sun, and H. Song, “Three-View Cotton Flower Counting through Multi-Object Tracking and Multi-Modal Imaging,” 2023 ASABE Annu. Int. Meet., pp. 1-, 2023, doi: 10.13031/AIM.202300895.

S. Wang, X. Zhang, H. Shen, M. Tian, and M. Li, “Research on UAV Online Visual Tracking Algorithm based on YOLOv5 and FlowNet2 for Apple Yield Inspection,” Proc. 4th WRC Symp. Adv. Robot. Autom. 2022, WRC SARA 2022, pp. 280–285, 2022, doi: 10.1109/WRCSARA57040.2022.9903925.

J. Feng, “Intelligent perception frameworks and algorithms for social good: food security and public safety,” IOWA State Univ., 2024, [Online]. Available: https://dr.lib.iastate.edu/entities/publication/f30a488e-a61f-4e95-8a6f-dc25ea36cdd3

B. Ji, J. Xu, Y. Liu, P. Fan, and M. Wang, “Improved YOLOv8 for small traffic sign detection under complex environmental conditions,” Franklin Open, vol. 8, p. 100167, Sep. 2024, doi: 10.1016/J.FRAOPE.2024.100167.

M. Khan et al., “Performance Evaluation of Machine Learning Models to Predict Heart Attack,” Mach. Graph. Vis., vol. 32, no. 1, pp. 99–114, 2023, doi: 10.22630/MGV.2023.32.1.6.

Engr. Ihtisham Ul Haq, Muhammad Anas, Waqas Ahmad, “Enhancing lane-keeping technologies with optimised convolutional neural networks for steering angle prediction,” Int. J. Veh. Auton. Syst., vol. 18, no. 1, pp. 1–20, 2025, doi: 10.1504/IJVAS.2025.10070324.

H. Yan, C. Chen, G. Jin, J. Zhang, X. Wang, and D. Zhu, “Implementation of a Modified Faster R-CNN for Target Detection Technology of Coastal Defense Radar,” Remote Sens. 2021, Vol. 13, Page 1703, vol. 13, no. 9, p. 1703, Apr. 2021, doi: 10.3390/RS13091703.

G. H. Latif Jan, Shah Hussain Bangash, Daud Khan, Atif Ishtiaq, Muhammad Imad, Mohsin Tahir, Waqas Ahmad, “Integrating Machine Learning and Deep Learning Approaches for Efficient Malware Detection in IoT-Based Smart Cities,” J. Comput. Biomed. Informatics, vol. 5, no. 2, pp. 280–299, 2023, [Online]. Available: https://jcbi.org/index.php/Main/article/view/246

K. Z. Thet and W. L. L. Phyu, “Green Chili Pepper Localization System Based on Mask R-CNN and IoT,” Proc. 21st IEEE Int. Conf. Comput. Appl. 2024, ICCA 2024, pp. 49–53, 2024, doi: 10.1109/ICCA62361.2024.10532882.