Deep Learning-Based Computer Vision Framework for Early Detection of Cocoa Plant Diseases in Precision Agriculture

DOI

10.2991/978-94-6463-878-3_27How to use a DOI?

Keywords

Cocoa Plant Disease; Computer Vision; Deep Learning; Precision Agriculture; YOLO

Abstract

Early detection of plant diseases is crucial for minimizing crop losses and ensuring sustainable agriculture, particularly in tropical regions. Cocoa (Theobroma cacao), a major cash crop, is highly susceptible to diseases such as Black Pod Rot and Monilia Pod Rot, which can severely impact yield. Conventional manual inspection methods are time-consuming, prone to error, and often implemented too late to prevent spread. This study proposes a real-time object detection framework using YOLOv8, a modern deep learning architecture, to identify cocoa pod diseases under natural field conditions. A custom dataset comprising 474 annotated images was collected from Jembrana, Bali, and enhanced using Roboflow-based augmentation. The YOLOv8n model was trained over 30 epochs and evaluated using standard object detection metrics. The model achieved a mAP@0.5 of 87.4%, mAP@0.5:0.95 of 74.1%, and an average inference time of 0.61 seconds per image, demonstrating high accuracy and suitability for edge deployment. The results validate the feasibility of using YOLOv8 for early-stage disease detection in cocoa, particularly in resource-limited environments. This work contributes to smart farming innovation by offering a lightweight, scalable solution for real-time agricultural diagnostics.

Copyright

© 2025 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)

TY  - CONF
AU  - I Putu Oka Wisnawa
AU  - Ni Nyoman Harini Puspita
AU  - I Putu Bagus Arya Pradnyana
AU  - I Komang Wiratama
AU  - I Made Dwi Jendra Sulastra
PY  - 2025
DA  - 2025/10/31
TI  - Deep Learning-Based Computer Vision Framework for Early Detection of Cocoa Plant Diseases in Precision Agriculture
BT  - Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2025 (ICOSTAS-EAS 2025)
PB  - Atlantis Press
SP  - 233
EP  - 242
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-878-3_27
DO  - 10.2991/978-94-6463-878-3_27
ID  - Wisnawa2025
ER  -