📄 中文摘要
茶叶是孟加拉国经济的重要资产，茶叶种植在推动经济发展中发挥着关键作用。然而，茶叶易受到多种叶部病害的侵袭，这可能导致产量下降和质量降低。手动检测这些病害既耗时又容易出错。为此，研究开发了一种基于teaLeafBD数据集的自动化深度学习模型，用于茶叶病害分类，以便更高效、便捷地检测病害。该数据集包含5,278幅高分辨率图像，图像被分为七个类别，其中六个类别代表不同的病害，另一个类别则代表健康叶片。通过该模型的应用，期望能够提高茶叶病害的检测准确性和效率。
基于深度学习模型的可靠茶叶病害诊断：通过可解释人工智能和对抗训练增强鲁棒性
📄 English Summary
Toward Reliable Tea Leaf Disease Diagnosis Using Deep Learning Model: Enhancing Robustness With Explainable AI and Adversarial Training
This study presents an automated deep learning model for tea leaf disease classification, utilizing the teaLeafBD dataset to facilitate easier and more efficient disease detection. Tea is a valuable asset for the economy of Bangladesh, and tea cultivation plays a crucial role in economic growth. However, tea plants are susceptible to various leaf infections, which can lead to reduced production and lower quality. Manual detection of these diseases is time-consuming and prone to errors. The teaLeafBD dataset consists of 5,278 high-resolution images categorized into seven classes, with six representing different diseases and one representing healthy leaves. The implementation of this model aims to enhance the accuracy and efficiency of tea leaf disease diagnosis.