A Comprehensive Review of Deep Learning-based Approaches to Corn Leaf Disease Detection

Machine Learning (ML) and Deep Learning (DL) have emerged as formidable companions for farmers, bestowing upon them cutting-edge resources and knowledge to improve decision-making, reduce losses, and foster efficient and environmentally friendly farming methods. A major danger to agricultural output, food security, and economic stability on a worldwide scale is corn leaf diseases. Detecting and diagnosing these diseases with traditional approaches is laborious, error-prone, and time-consuming due to the reliance on human examination. New developments in DL provide hope for quick, accurate, and automated recognition of corn leaf diseases. This study takes a close look at the most recent developments in the field of DL-based corn leaf disease detection. To tackle issues including occlusion, changing environmental circumstances, and inter-class similarities across diseases, it emphasizes the use of convolutional neural networks (CNNs), transfer learning, and hybrid models. Datasets, preprocessing methods, and assessment measures that are accessible to the public are also included in the study. This work seeks to provide academics and practitioners with a thorough grasp of the present state of DL for identifying corn leaf diseases, as well as an overview of forthcoming developments in the field.