Enhancing Plant Disease Detection in Image Processing: A Comprehensive Review

Abstract

Plant disease detection is crucial for global food security and sustainable agriculture. Image processing techniques offer non-intrusive and rapid disease identification. However, their efficacy depends on carefully selected hyperparameters, significantly impacting accuracy and efficiency. This review explores the significance and challenges of using hyperparameters in plant disease detection through various classification schemes and methodologies. It addresses computational costs and emphasizes the need for efficient approaches. Hyperparameter tuning enhances system performance, demonstrating the potential of deep learning architectures with specific hyperparameters. This review provides insights for future research, advancing sustainable agriculture and global food security.