Wheat leaf diseases classifcation using deep learning techniques

Abstract

Wheat is one of the most important staple crops in the world, and leaf diseases can signifcantly reduce its yield and quality. In this study, we propose a deep learning approach for wheat leaf disease classifcation. We collected a large dataset of wheat leaf images and applied appropriate preprocessing techniques to enhance the quality of the data. Then, we trained a convolutional neural network (CNN) model on the preprocessed dataset and used a genetic algorithm for hyperparameters optimization. Our proposed CNN model achieved an overall accuracy of 98.08% and the other metrics scores ranged from 97% to 100%. We also developed a web app and mobile app for farmers and other stakeholders to easily access and utilize the model. Our work demonstrates the potential of deep learning techniques for accurate and timely diagnosis of wheat leaf diseases, which can ultimately improve crop yield and help sustain food security.