A Review on Tomato Leaf Disease Detection using Deep Learning Approaches

Abstract

Agriculture is one of the major sectors that influence the India economy due to the huge population and ever-growing food demand. Identification of diseases that affect the low yield in food crops plays a major role to improve the yield of a crop. India holds the world's second-largest share of tomato production. Unfortunately, tomato plants are vulnerable to various diseases due to factors such as climate change, heavy rainfall, soil conditions, pesticides, and animals. A significant number of studies have examined the potential of deep learning techniques to combat the leaf disease in tomatoes in the last decade. However, despite the range of applications, several gaps within tomato leaf disease detection are yet to be addressed to support the tomato leaf disease diagnosis. Thus, there is a need to create an information base of existing approaches and identify the challenges and opportunities to help advance the development of tools that address the needs of tomato farmers. The review is focussed on providing a detailed assessment and considerations for developing deep learning-based Convolutional Neural Networks (CNNs) architectures like Dense Net, ResNet, VGG Net, Google Net, Alex Net, and LeNet that are applied to detect the disease in tomato leaves to identify 10 classes of diseases affecting tomato plant leaves, with distinct trained disease datasets. The performance of architecture studies using the data from plantvillage dataset, which includes healthy and diseased classes, with the assistance of several different architectural designs. This paper helps to address the existing research gaps by guiding further development and application of tools to support tomato leaves disease diagnosis and provide disease management support to farmers in improving the crop.