Tea Leaf Disease Classification Paper Published in IEEE Xplore
Our paper Beyond the Leaf: Intelligent Lightweight Disease Detection in Tea Plants with Spatial Convolutional Neural Networks and Explainable AI has been published in IEEE Xplore — 2025 IEEE 7th International Conference on Sustainable Technologies For Industry 5.0 (STI).
About the Paper
Tea is one of the most economically significant beverages in Bangladesh. Traditional methods for diagnosing tea leaf diseases depend on pathologists to identify symptoms visually, which often results in misdiagnosis and lengthy detection processes. This paper proposes a lightweight Convolutional Neural Network (CNN) to address this, enabling automatic classification of tea leaf diseases with high accuracy and low computational cost.
Key Contributions
- Proposed a lightweight spatial CNN for tea leaf disease classification
- Successfully classifies six types of tea leaf diseases with 99.23% accuracy
- Outperforms MobileNetV2 (91.23%) and Xception (91.66%) on the same dataset
- Significantly reduced parameter count for deployment on resource-constrained devices
- Grad-CAM visualization applied to explain model predictions
Results
| Model | Accuracy |
|---|---|
| Proposed CNN | 99.23% |
| MobileNetV2 | 91.23% |
| Xception | 91.66% |
Citation
R. H. Prince, M. O. F. Goni, H. I. Peyal, and R. K. Kundu, “Beyond the Leaf: Intelligent Lightweight Disease Detection in Tea Plants with Spatial Convolutional Neural Networks and Explainable AI,” in Proc. 2025 IEEE 7th International Conference on Sustainable Technologies For Industry 5.0 (STI), IEEE, 2025, pp. 1–6.