Abstract:
Rapid and precise disease detection can considerably boost the sustainable agricultural yield of tomato plants. The conventional method allows for human agricultural professionals to recognize irregularities in tomato plants caused by pests, sickness, bad weather, and nutrient shortages. Initially, less precise traditional processing of image and artificial intelligence approaches are being used to automatically identify diseases in tomato leaves. To improve accuracy of prediction, deep neural network-based categorization is implemented. This article introduces a thorough analysis of current research on the tomato leaf detection diseases via image processing, machine learning, and deep neural network methods. Discuss the methods employed and deep learning frameworks that have been adopted, as well as the public and private datasets that may be utilized to detect tomato leaf disease. As a consequence, suggestions are made on how to choose the best approaches in order to increase forecast accuracy. The complexities faced when a the machine learning and deep neural network models are then outlined.
