Leveraging the WFD2020 Dataset for Multi-Class Detection of Wheat Fungal Diseases with YOLOv8 and Faster R-CNN

Abstract

Wheat fungal infections pose a danger to the grain quality and crop productivity. Thus, prompt and precise diagnosis is essential for efficient crop management. This study used the WFD2020 image dataset, which is available to everyone, to look into how deep learning models could be used to find powdery mildew, leaf rust, and yellow rust, which are three common fungal diseases in Punjab, India. We changed a few hyperparameters to test TensorFlow-based models, such as SSD and Faster R-CNN with ResNet50, ResNet101, and ResNet152 as backbones. Faster R-CNN with ResNet50 achieved a mean average precision (mAP) of 0.68 among these models. We then used the PyTorch-based YOLOv8 model, which significantly outperformed the previous methods with an impressive mAP of 0.99. YOLOv8 proved to be a beneficial approach for the early-stage diagnosis of fungal diseases, especially when it comes to precisely identifying diseased areas and various object sizes in images. Problems, such as class imbalance and possible model overfitting, persisted despite these developments. The results show that YOLOv8 is a good automated disease diagnosis tool that helps farmers quickly find and treat fungal infections using image-based systems.