CNN-Based Machine Learning Model for Disease Prediction in Crops

Potato crops are vital to global food security, but they are susceptible to several diseases that hinder growth and yield. Traditional methods of detecting these diseases rely on labor-intensive lab tests and human observation. This research presents an enhanced machine learning model for detecting and categorizing potato leaf diseases, specifically early blight and late blight, using Convolutional Neural Networks (CNN). The model is trained on various datasets of potato leaf images, utilizing techniques such as hyper-parameter tuning, data augmentation, and transfer learning. The proposed model attains an accuracy of 96.11%, significantly improving upon existing methods. Image processing techniques, Segmentation is performed using K-means technique and feature extraction is done by utilizing gray-level co-occurrence matrix, along with multi-class support vector machines for classification, are employed. Additionally, the study shows that CNN performs better than Artificial Neural Networks (ANN) in image classification. The study demonstrates how AI and deep learning technology can be used in agriculture to improve crop management and enable early disease prediction. Experiments have been conducted using the real image dataset.