Demystifying the Role of Deep Learning Models for Disease Detection and Classification in Solanaceae Crops

Deep learning has emerged as a promising image processing and data analysis technique that is being successfully applied in various domains. Recently, there has been extensive work in employing deep learning techniques to various agricultural and food production challenges. In the agricultural sector, the use of Convolutional Neural Networks, transfer learning, object detection, and semantic segmentation models has led researchers and practitioners to realize phenomenal progress in automating the classification and diagnosis of plant diseases. This chapter presents a detailed analysis of deep learning techniques and models for disease detection, particularly, Solanaceae crops. It discusses intersections of traditional and deep learning approaches for disease detection in Solanaceae crops which tend to have significant socio-economic impact in the Asian and African cultures. It highlights the existing and future potential of DL models in disease management outcomes in Solanaceae crops that play an important role in contributing to food security and income earning for smallholder farmers.