Plant Disease Detection Using Mask RCNN

Abstract

In this study, we introduce a new approach to automate the identification of plant diseases using machine learning methods, particularly focusing on the Mask R-CNN model. Plant diseases pose a significant threat to agricultural productivity and economic value, requiring efficient detection methods. Leveraging various morphological features and properties of plant leaves, our framework aims to accurately identify different types of plant diseases. Furthermore, we present Mask R-CNN, an all-encompassing system for segmenting individual objects within an image, crucial in various computer vision tasks. Mask R-CNN builds on the Faster R-CNN model by effectively identifying objects within images and producing detailed segmentation masks for each instance. We show the success of Mask R-CNN in addressing various complex problems, including instance segmentation, outperforming existing methods.