One of the biggest reasons for financial losses in the agriculture sector is plant disease, which is described as an abnormal condition that interferes with a plant's natural growth. Increasing agricultural crop output requires early detection of plant diseases. In this study, a novel robust hybrid classification model that permits real-time disease classification in tomato, grape, and apple plants has been created. It is based on swarm optimization-supported feature selection and includes machine learning and deep learning methods. This will allow for the early diagnosis of the plant illness and the application of the proper remedy. This study presents the development of a new hybrid plant leaf disease classification model with low computational complexity and high accuracy. The model consists of a convolutional neural network (CNN) classifier and the wrapper approach, which includes the flower pollination algorithm (FPA) and support vector machine (SVM) and a wrapper-based feature selection approach using metaheuristic optimisation techniques. Using wavelet families including biorthogonal, Coiflets, Daubechies, Fejer–Korovkin, and symlets, a two-dimensional discrete wavelet transform (2D-DWT) was used to extract the characteristics from the picture dataset, which included apple, grape, and tomato plants.

Detection of Plant Diseases, Machine Learning, Deep Learning Methods, Swarm Optimization-Supported Feature.