A Systematic Comprehension of DL Models for Categorizing Plant Diseases

Plants play a significant role in human life, serving as sources of medicine, food, and other essential resources. Plant disease classification is an important task in agriculture, as it enables early detection and treatment of diseases, leading to improved crop yield and quality. Deep learning models, particularly convolutional neural networks (CNNs), have shown great potential in image classification tasks and modeling complex processing applications with extensive data, including plant disease identification. This study highlights the potential of artificial intelligence (AI) in the agricultural sector, specifically for plant disease detection and classification. In this article, we discussed the various datasets and deep learning models used for plant disease classification and analyzed their performance. We also presented an overview of the data preprocessing and data augmentation techniques used to improve model accuracy. Additionally, we examined the challenges and limitations of deep learning in plant disease classification and suggested a few future research directions. This survey will serve as a comprehensive resource for researchers and practitioners in the agricultural sector to understand the current state of the art in plant disease classification using deep learning and to identify areas for further research.