Advanced Image Classification for Corn Leaf Disease Detection: A Deep Learning Approach

This research presents a deep learning-based framework for the accurate detection and classification of corn leaf diseases, addressing critical challenges in agricultural disease management. The proposed approach integrates three distinct classifiers: a modified VGG16-based model, a custom Convolutional Neural Network (CNN), and a Generalized Regression Neural Network (GRNN). Utilizing a dataset of 3,852 corn leaf images spanning four disease classes, we applied a comprehensive preprocessing pipeline comprising resizing, normalization, class weight adjustments, and data augmentation to enhance model robustness. Our models were trained using the Adam optimizer, and their performance was rigorously evaluated through accuracy, loss metrics, and statistical validation using an Analysis of Variance (ANOVA) test. The VGG16-based model achieved the highest classification accuracy of 95.05%, demonstrating its efficacy in distinguishing visually similar diseases. Compared to traditional methods, this approach not only improves disease detection accuracy but also provides a scalable solution for precision agriculture. These results highlight the potential of deep learning in enhancing crop health monitoring and reducing agricultural losses.