Using Region-Based Deep Learning Algorithm Mask RCNN Algorithm on Image-Based Plant Disease Detection

In this study, we propose a plant disease detection system that combines the power of regular Convolutional and Mask Region-Based Convolutional Neural Networks models to accurately identify and classify plant-based leaf diseases through visual symptoms. The proposed model achieves an accuracy rate of 98% using the CNN model on the Plant Village dataset, showcasing its effectiveness in disease classification. By integrating Mask R-CNN, our system offers precise instance segmentation, providing detailed information on disease-affected regions within leaf images, which is crucial for targeted treatment strategies. This paper explores using deep learning and image processing methods to transform agricultural practices that will give farmers a reliable instrument for detecting and preventing diseases early. The proposed system contributes to sustainable agriculture, enhancing crop management and ensuring global food security. Combining CNN and Mask R-CNN models offers a robust solution for efficient plant disease detection, revolutionizing agricultural practices. The model will provide farmers and agronomists with a reliable way for early disease detection, facilitating timely interventions to reduce the destruction of crops and improve food availability. This paper contributes to the field of prevention systems for automated plant disease management, promoting sustainable agriculture practices worldwide.