Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199703,
        author = {J.VETRIMANIKUMAR and K.MUTHU KAMATCHI and S.MANIKANDAN and N.MOHAMED UVAIS},
        title = {Coconut Leaf Disease Detection Using YOLOv8: A Web-Based Approach},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {728-736},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199703},
        abstract = {Agricultural sustainability in tropical regions is closely connected to the health of plantation crops. In India, coconut cultivation supports a large number of rural households and contributes significantly to the agricultural economy. However, coconut plantations are frequently affected by diseases and pest attacks that reduce productivity. Farmers generally depend on manual observation to identify leaf diseases, but this approach often results in delayed diagnosis and inconsistent assessments. 
This study presents a deep learning–based approach for detecting coconut leaf diseases using the YOLOv8s deep learning object detection model. The system is trained using a publicly available dataset obtained from Kaggle containing nearly 1,500 images of coconut leaves. The dataset includes four classes representing different leaf conditions: Healthy, Leaf Spot, Yellowing, and Pest Damage. Images were divided into training and testing subsets with an 80:20 ratio. 
Model training and evaluation were carried out using Python within the Ultralytics deep learning framework. The YOLOv8s architecture was selected because of its efficient design and ability to perform object detection with low computational requirements. Its anchor-free detection strategy and feature extraction layers enable the model to recognize disease patterns and localize affected regions within leaf images. 
Experimental evaluation shows that the trained model can successfully identify disease symptoms across images captured under different environmental conditions such as varying illumination and complex natural backgrounds. Due to its relatively fast inference speed, the system can potentially be integrated into mobile-based diagnostic tools that allow farmers to assess plant health directly in the field. The proposed approach demonstrates how deep learning can support precision agriculture by enabling early disease detection and improving plantation management.},
        keywords = {Coconut leaf disease, YOLOv8s, Deep learning, Object detection, Computer vision.},
        month = {May},
        }