Classification of Corn Diseases Using Convolutional Neural Networks and Support Vector Machine

Recent progress in detecting diseases in plant leaves by using image analysis to hаs led to a re-evaluation of farming methods. Automated detection systems swiftly identify problems in roots, stems, leaves, and fruits, enabling farmers to easily diagnose plant diseases through images. This approach not only saves time and cuts costs, but also facilitates remote monitoring and support for farmers. This study underscores the pivotal role of machine learning, particularly in computer vision, within the realm of agriculture. Evaluating models that based on Convolutional Neural Network (
$\text{CNN}$
) and Support Vector Machine (
$\text{SVM}$
) techniques for classifying corn leaf disease reveals the superior accuracy of CNN at 99.8% compared to SVM at 99.1%. Uniformity in training parameters enhances the study's reliability. Dataset capacity was increased using augmentation. The emphasis on interpretability and the exploration of additional techniques paves the way for advancing precision agriculture through computer vision. This research makes a great contribution to the field, showcasing the effectiveness of the proposed methodology and offering valuable directions for future investigations.