Integrated Rasnet Model for Efficient Automated Assessment and Sorting of Leaf Diseases in Agriculture

A novel integrated methodology for the automated assessment and sorting of leaf diseases in agricultural settings is provided in this work. The method improves the efficiency and accuracy of disease evaluation by combining deep learning and machine learning methodologies. Pre-processing techniques like contrast enhancement and color space conversion are the first steps in the research process since they set the conditions for further investigation. K-Means clustering is used to divide the image into regions, enabling user input for the purpose of selecting the disease region. In this work we proposed RASNet model (Recurrent and SVM Hybrid Network for Enhanced Leaf Disease Classification). A more complete texture analysis is made possible by highlighting the significance of picture preprocessing. The purpose of introducing a Recurrent Neural Network (RNN) strategically is to extract temporal dependencies and sequential patterns from picture data. Combined with carefully collected texture data, these RNN outputs help classify diseases using a Multiclass Support Vector. We have used images of leaves affected by different bacterial and fungal diseases: Alternaria Alternata, Anthracnose, Bacterial Blight and Cercospora Leaf Spot in our experiment and our proposed method.