An Analytical Study of Assorted and Resilient Rice Blast Varieties Using Deep Learning Techniques

The following presents a novel technique that can be used for automated disease identification in plants by combining a Convolutional Neural Network (CNN) and Support Vector Machine (SVM) classifier. The suggested CNN-SVM model is trained and evaluated on a dataset that consists of images of healthy and diseased plant leaves. Classification performance assessment includes such metrics as certainty rate, recall, F1 score, instance count, instance ratio, and accuracy. The outcomes indicate its excellent classification ability across different diseases such as the Healthy class with an 88.17% recall rate and 95% accuracy. Additional categories including Leaf Blast, Neck Blast, Node Blast, and Panicle Blast show good competitive performance in terms of precision, recall, and F1-score. Overall, the proposed approach shows promise in the accurate and effective classification of plant diseases with potential benefits for crop management toward sustainable agriculture.