Ensemble Learning for Plant Leaf Disease Detection: A Novel Approach for Improved Classification Accuracy

Abstract

Abstract Plant leaf diseases pose significant threats to agricultural productivity and food security. Accurate and timely detection of these diseases is crucial for effective disease management. This research paper proposes a novel approach for plant leaf disease detection using ensemble learning. Ensemble learning combines multiple base models to improve classification accuracy by leveraging their collective intelligence. The proposed ensemble model integrates Convolutional Neural Networks (CNN), ResNeXt, and InceptionV3 architectures, exploiting their diverse strengths in image classification tasks. Extensive experiments on a diverse dataset demonstrate that the ensemble model outperforms individual base models, achieving higher classification accuracy. Its ability to capture complementary features enhances generalization and robustness against variations in disease patterns and image quality. The ensemble model also offers benefits such as improved interpretability, model stability, and reduced overfitting risks. The proposed approach contributes to the advancement of automated plant disease diagnosis systems, enabling early detection and timely intervention to mitigate crop losses and ensure food security. By combining multiple models, the ensemble learning approach improves the accuracy and reliability of plant leaf disease detection, addressing a critical need in agricultural practices.