CBAM-Enhanced YOLOv8: An Attention-Based Approach for Tomato Disease Detection

DOI

10.2991/978-94-6463-910-0_36How to use a DOI?

Keywords

Tomato disease detection; YOLOv8; Smart agriculture; Image classification; Plant pathology

Abstract

The severity of tomato foliar diseases greatly affects tomato yield and quality. The current method for identifying such diseases relies on manual inspection, which is time-consuming and error-prone. To address this issue, we developed an automatic and accurate detection model based on YOLOv8 integrated with a Convolutional Block Attention Module (CBAM). The inclusion of CBAM enables the network to focus more effectively on disease-relevant regions and suppress background noise, which is particularly beneficial for distinguishing between visually similar tomato leaf diseases. A custom dataset containing more than 1,200 annotated images was constructed from two sources: field-captured tomato leaf images and publicly available data from the PlantVillage dataset on Kaggle (https://www.kaggle.com/datasets/emmarex/plantdisease/data?select=PlantVillage). The dataset covers 10 categories, including nine common tomato leaf diseases and healthy leaves, with variations in lighting, leaf orientation, and background complexity to simulate real-world conditions. This diversity enhances the model’s generalization ability and reliability in practical applications.

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  - Yuqi Lai
PY  - 2025
DA  - 2025/12/15
TI  - CBAM-Enhanced YOLOv8: An Attention-Based Approach for Tomato Disease Detection
BT  - Proceedings of the 2025 2nd International Symposium on Agricultural Engineering and Biology (ISAEB 2025)
PB  - Atlantis Press
SP  - 337
EP  - 346
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6463-910-0_36
DO  - 10.2991/978-94-6463-910-0_36
ID  - Lai2025
ER  -