Turmeric plant disease detection

In this study, we developed a deep learning model for classifying turmeric leaf diseases, focusing on leaf spot, leaf blotch, and healthy leaves. We compiled a diverse, balanced dataset of high-resolution turmeric leaf images and applied standard preprocessing techniques like resizing, normalization, and data augmentation to prepare the data. Our approach combines the MobileNet architecture for efficient feature extraction with a Support Vector Machine (SVM) for classification, optimizing both image processing capabilities and classification accuracy. This hybrid model, using MobileNet to extract features and SVM for classification, was specifically designed to improve disease detection in turmeric crops. The experimental results, based on a well-structured division of training and validation sets, were promising, indicating the effectiveness of integrating deep learning with traditional machine learning techniques for accurate diagnosis of crop diseases. This approach has significant implications for agriculture, enhancing crop management and disease control through precise, automated disease detection. Keywords: Turmeric, leaf disease, deep learning, MobileNet, SVM, classification, agriculture, disease detection.