A Comprehensive Review and Discussion of Segmentation based Tomato Plant Disease Detection Approaches

These days, agriculture is essential to human existence, and currently, approximately 70% of the world's population is engaged in some form of agricultural activity, whether directly or indirectly. In the old and existing system, there are no methods to identify diseases in diverse crops in an agricultural environment. The most affected crops due to such diseases are tomatoes, and due to this problem, the rate of tomato production is very high. Tomato diseases control growth and production; hence, early diagnosis and disease detection are also essential. Better yields can be achieved through early disease diagnosis and treatment in tomato plants. Tomato plants naturally get diseases, and if the right measures aren't taken to treat them, it may have a major impact on the quality, quantity, and productivity of the crop. In spite of the numerous failed attempts to apply machine learning techniques for disease detection and classification of tomato plant diseases. New developments in a branch of image processing known as clustering-based segmentation have given researchers new reasons to be optimistic about the future of their discipline. So, in this paper, we present a comprehensive review and discussion of segmentation-based tomato plant disease detection approaches to identify the best algorithms. The purpose of this review is to investigate the possibilities of clustering-based tomato plant disease detection using swarm optimization techniques in order to allow future research into improving the system's performance and accuracy.