Optimization of Mask R-CNN Architecture for Accurate Identification and Segmentation of Potato Plant Leaf Diseases in Agriculture

Abstract

A sizable section of India's rural population depends on agriculture for their livelihoods, while manual labor and disease control continue to be problems. The objective of this study is to enhance the Mask R-CNN architecture for precise detection and segmentation of potato plant leaf illnesses. This is of utmost importance in agriculture since diseases like as early blight and late blight profoundly affect crop productivity. Traditional illness detection techniques are characterized by their high labor requirements and susceptibility to human mistakes, thereby requiring the use of automated alternatives. By refining the feature extraction method, optimizing the Region Proposal Network (RPN), and enhancing segmentation via data augmentation and parameter tweaking, the suggested technique improves Mask R-CNN. Empirical findings indicate that the optimized Mask R-CNN outperforms other models, including YOLOv8 and EfficientNet, with an accuracy of 99.86%, precision of 99.82%, recall of 99.83%, and an F1-score of 99.84%. In conclusion, of work establishes that the optimized Mask R-CNN is a reliable instrument for early and accurate disease identification, thereby enhancing crop management and agricultural output.