Citation

Ramamonjison, Kiady Fanomezantsoa and Sin, Yew Keong and Tan, Yi Fei (2025) Soybean Root Branches Classification Using YOLO. In: 2025 Multimedia University Engineering Conference, MECON 2025, 21 July 2025 - 23 July 2025, Cyberjaya, Malaysia.

Text 477.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

The use of imaging techniques for plant root phenotyping is becoming increasingly vital in modern agriculture for assessing root traits and improving crop management. This study presents a deep learning-based approach using the You Only Look Once (YOLO) v8 model to classify soybean root images based on the number of root branches. The main objective is to design a reliable and efficient classification system capable of automatically distinguishing soybean roots with either many or few branches, to support scalable and consistent root trait evaluation. The Soybean Root Image Dataset was utilized for model training and evaluation. Images were preprocessed through data splitting (training and validation) and augmented to balance the two classification categories: "many" and "less" root branches. The model was trained for 10 epochs, achieving an accuracy of 98.53%. Class-wise performance showed an F1-score of 99.16% for the "many" class (precision: 100%, recall: 98.33%) and 94.12% for the "less" class (precision: 88.89%, recall: 100%). These results highlight the effectiveness of YOLO v8 in classifying root structures with high precision, demonstrating its potential for automated plant phenotyping applications. Future research could explore extending this approach to more complex root traits and integrating it into precision agriculture systems.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	precision agriculture, yolo, soybean root classification, deep learning in agriculture, plant root phenotyping
Subjects:	H Social Sciences > HD Industries. Land use. Labor > HD1401-2210 Agriculture
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	19 Mar 2026 01:23
Last Modified:	19 Mar 2026 01:23
URII:	http://shdl.mmu.edu.my/id/eprint/15491

Downloads

Edit (login required)