Roses Plant Disease Detection using DenseNet121 Model

Roses diseases pose a significant threat to horticultural productivity, necessitating early detection and intervention for effective management. This research proposes the development of a web-based application leveraging Deep Learning (DL) methodologies to facilitate rapid and accurate disease identification in roses. The application will employ a pre-trained Convolutional Neural Network (CNN) model, DenseNet121, fine-tuned on a curated dataset of rose disease images through transfer learning. Users will be able to upload images of their plants via the web interface, which will then be analyzed by the DenseNet121 model to identify potential diseases. This DL-powered tool aims to empower gardeners and horticulturists with a user-friendly platform for early disease detection and proactive management, ultimately contributing to healthier rose cultivation practices. The research will investigate the effectiveness of DenseNet121 for detecting rose diseases, assess the accuracy of the web application across various disease types, and explore the practical implications of integrating such a tool into real-world horticultural settings.