Leveraging YOLOv8 and YOLOv11 for Real-Time Leaf Image Analysis for Plant Disease Detection

Plant diseases pose a significant threat to agriculture. This proposed work aims to develop a machine learning-based framework for automatically detecting plant diseases using image recognition and machine learning techniques. We considered two classes, healthy and diseased, covering twenty-nine different diseases. A convolutional neural network (CNN) was employed for feature extraction and classification. The general approach began with image preprocessing to ensure uniformity in size and format. The model achieved an overall accuracy of over 68%, effectively classifying specific diseases into respective categories. The findings confirm the potential of machine learning techniques in agricultural applications, particularly in identifications plantation corpus. However, further experiments are suggested to integrate this model into a comprehensive real-time monitoring system for timely intervention.