Published Paper Details:

Tea leaves are susceptible to various diseases that can significantly impact the yield and quality of tea production. Early detection and diagnosis of these diseases are crucial for timely interventions and effective disease management. In recent years, deep learning techniques have shown promising results in automated image-based disease detection systems. This study investigates the application of pretrained convolutional neural networks (CNNs), specifically AlexNet and GoogleNet, for tea leaves disease detection. The pretrained AlexNet and GoogleNet models are fine-tuned using a large dataset of labeled tea leaf images containing healthy leaves as well as leaves affected by common diseases. . The results demonstrate the effectiveness of using pretrained networks for tea leaves disease detection, with both AlexNet and GoogleNet achieving high accuracies. Additionally, the models are compared in terms of computational efficiency and detection performance to determine their suitability for practical deployment. Proposed methodology uses Tea Leaves Disease Classification dataset classify seven types of diseases like red leaf spot, gray blight, white spot, brown blight, algal leaf spot, Anthracnose, bird's eye spot each class contain minimum 40 images proposed methodology compute tea leaves diseases identification by using AlexNet and GoogleNet. The methodology proposed Convolutional Neural Network (CNN) to improve accuracy further experimental results show the detection and identification accuracy Of AlexNet and GoogleNet for tea Leaves diseases.