Potato and Tomato Crop Disease Prediction Using Advanced Machine Learning Techniques

Agriculture is important for global food security, yet crop diseases continue to damage and reduce yields. Diseases in potato and tomato plants present serious challenges to farmers as timely detection and management is required. This research showcases a comparative study of three machine learning models, Convolutional Neural Networks, Support Vector Machine and Random Forest Classifier. The methodology involves preprocessing images taken from Plant Village dataset with Contrast Limited Adaptive Histogram Equalization (CLAHE) to improve image quality, followed by comparative study of classification approaches. Although CNNs obtain better accuracy by automatically drawing features, SVM and Random Forest classifiers give an overview of how traditional machine learning algorithms work. The findings explain the pros and cons of these methods and therefore outline a complete solution for an efficient and scalable crop disease detection system.