Detection of Maize Leaf Diseases Via Image Analysis

Abstract

A variety of leaf diseases affecting maize plants led to a notable reduction in crop yield, both in terms of quantity and quality. Traditional visual detection of these diseases was prone to subjectivity and limited accuracy. Therefore, advanced machine learning (ML) and deep learning (DL) techniques were explored to improve classification and detection practices in agricultural research. This study focused on employing ML and DL methodologies for the automated classification of maize leaf diseases, utilizing the "Corn or Maize Leaf Disease Dataset," which includes images of leaves affected by diseases such as common rust, blight, and gray leaf spot, alongside healthy samples. Four algorithms were implemented and evaluated: Convolutional Neural Networks (CNN) and Artificial Neural Networks (ANN). The models were trained on the dataset to identify disease patterns and characteristics in maize leaves. The results indicated that the CNN model achieved an accuracy of 95%, demonstrating its superior capability in image classification tasks. while ANN 85%. The comparative analysis provided a comprehensive understanding of the strengths and limitations of each algorithm in the context of maize leaf disease detection. The study concluded that deep learning models, particularly CNNs, are highly effective in this domain, offering precise and efficient disease management with minimal manual intervention. These findings offer valuable insights for future agricultural research and highlight the potential of integrating advanced computational techniques to optimize agricultural diagnostics and enhance crop management.