Assessing algorithms for sugar cane pest and disease detection: a developmental perspective
Sugarcane pest and disease detection consider techniques in precision agriculture that would not only be expected to maintain the crops' health but even improve their yields. This research proposes assessing the various detection algorithms for their efficiency in detecting and classifying sugarcane diseases, including Deep Learning (CNN, ResNet, YOLO), Machine Learning (SVM, Random Forest, K-NN), Image Processing, and Hybrid Approaches.