Unveiling the Enigma: Advancing Rose Leaf Disease Detection with Transformed Images and Convolutional Neural Networks

In this article, we unravel the mysteries of rose leaf disease detection and explore the transformative potential of Convolutional Neural Networks (CNNs) in this domain. Roses, renowned for their elegance and beauty, are highly susceptible to various leaf diseases that can significantly impact their health and vitality. Leveraging the power of CNNs, we investigate the application of advanced machine learning techniques to accurately identify and classify different types of rose leaf diseases. Using a dataset comprising 14,910 images of rose leaves across three categories—Healthy Leaf Rose, Rose Rust, and Rose Sawfly/Rose Slug—we employ state-of-the-art data augmentation techniques to enhance the diversity and robustness of our training data. Through comprehensive experimentation and rigorous evaluation, our CNN model achieves an impressive validation accuracy of 95.65%, showcasing its potential as a reliable tool for early disease detection in roses. By shedding light on the intricacies of rose leaf disease detection and harnessing the capabilities of CNNs, our research contributes to the advancement of plant pathology, paving the way for effective disease management and sustainable cultivation practices in the world of roses.