Enhancing Tea Leaf Disease Recognition with Attention Mechanisms and Grad-CAM Visualization

2025-12-19

AI Summary

To address the low efficiency and high latency of manual diagnosis of tea plant diseases—leading to substantial economic losses—this paper proposes an automated tea leaf disease recognition system. We construct a dedicated dataset comprising 5,278 images across seven disease classes and introduce a novel channel-spatial dual-attention mechanism to enhance discriminative feature representation. Furthermore, we integrate three state-of-the-art transfer learning models—DenseNet, Inception, and EfficientNet—and employ Grad-CAM to generate pixel-level lesion heatmaps for improved model interpretability. Experimental results demonstrate that the ensemble model achieves an accuracy of 85.68%, significantly outperforming individual baseline models. The proposed dual-attention module and the publicly available, domain-specific dataset jointly advance intelligent tea disease diagnosis by providing both a novel methodological framework and essential benchmark resources.

Technology Category

Computer Vision: Interpretability, Explainability, and TransparencyMachine Learning: Ensemble MethodsKnowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

Web Mining and Content Analysis: Large pretrained models with web dataSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingResponsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Tea is among the most widely consumed drinks globally. Tea production is a key industry for many countries. One of the main challenges in tea harvesting is tea leaf diseases. If the spread of tea leaf diseases is not stopped in time, it can lead to massive economic losses for farmers. Therefore, it is crucial to identify tea leaf diseases as soon as possible. Manually identifying tea leaf disease is an ineffective and time-consuming method, without any guarantee of success. Automating this process will improve both the efficiency and the success rate of identifying tea leaf diseases. The purpose of this study is to create an automated system that can classify different kinds of tea leaf diseases, allowing farmers to take action to minimize the damage. A novel dataset was developed specifically for this study. The dataset contains 5278 images across seven classes. The dataset was pre-processed prior to training the model. We deployed three pretrained models: DenseNet, Inception, and EfficientNet. EfficientNet was used only in the ensemble model. We utilized two different attention modules to improve model performance. The ensemble model achieved the highest accuracy of 85.68%. Explainable AI was introduced for better model interpretability.

Problem

• Automated classification of tea leaf diseases to reduce economic losses
• Improving disease recognition accuracy with attention mechanisms and ensemble models
• Enhancing model interpretability using Grad-CAM visualization for explainable AI

Innovation

• Attention mechanisms enhance model performance
• Grad-CAM provides explainable AI visualization
• Ensemble model combines EfficientNet for accuracy