Phytoscan: Advanced Rice Leaf Disease Detection using Efficientnet-B5

One of the most extensively grown crops in the world is rice (Oryza sativa), which is a staple food throughout South Asia. However, rice leaf diseases cause large production losses annually and represent a danger to agricultural productivity and economic stability. Time-Consuming and requiring expert analysis, laboratory testing is the foundation of traditional illness detection methods, underscoring the need for automated and effective solutions. Because DenseNet201 is a very deep network, improper regularization could lead to overfitting. Additionally, the study only looks at diseases that affect rice leaves, although a wider range of diseases might improve robustness. The lack of explainability methodologies, which could aid in comprehending how models interpret disease traits and increase their credibility for agricultural specialists, is another significant disadvantage. A deep learning-based method for detecting rice leaf disease utilizing the EfficientNetB5 architecture is suggested to overcome these drawbacks. To successfully diagnose the main rice leaf illnesses, EfficientNetB5 is trained on a dataset of images of both healthy and diseased rice leaves using transfer learning. The suggested method offers an automated and scalable early disease detection option, allowing farmers to reduce crop losses and take prompt preventive action. Precision agriculture is advanced by EfficientNetB5, which offers a more precise, effective, and scalable method of detecting rice leaf disease. By using cutting-edge deep learning techniques, this research advances precision agriculture and increases the efficiency of rice production.