AI-Driven Banana Leaf Disease Detection Using Deep Learning Models

Authors

  • Ashish K. Patil Department of Computer Applications, GH Raisoni College of Engineering and Management, Jalgaon, India
  • Yogesh Laandge Department of Computer Applications, GH Raisoni College of Engineering and Management, Jalgaon, India

Keywords:

Agricultural Technology, Convolutional Neural Networks (CNNs), Deep Learning, MobileNetV2, EfficientNet, DenseNet.

Abstract

The stability of the global food supply and agricultural economies is critically dependent on crop health, which is persistently threatened by a variety of plant diseases. To safeguard yields, minimize excessive pesticide use, and promote sustainable cultivation, the implementation of rapid and precise disease identification systems is paramount. Conventional techniques that depend on visual inspection by agronomists are not only slow and subjective but also unfeasible for widespread monitoring. The rise of sophisticated artificial intelligence (AI) and deep learning has now enabled the development of automated, non-destructive diagnostic tools using computer vision. This study conducts a detailed comparative assessment of several deep learning models tailored to detect specific, high-impact diseases in banan plants namely Black Sigatoka, Yellow Sigatoka, Panama Disease, and Potassium Deficiency while also categorizing healthy leaves. We trained and evaluated a suite of architectures, including a custom Convolutional Neural Network (CNN), MobileNetV2, EfficientNet, and DenseNet, on a meticulously prepared dataset of leaf imagery. Our findings indicate that MobileNetV2 outperformed other models, attaining superior classification accuracy and a consistent balance between precision and recall across all disease categories. This highlights its suitability as an efficient and dependable framework for automated plant disease diagnosis. The research confirms that AI-powered systems can offer farmers a practical, real-time solution for crop health monitoring, facilitating informed agricultural management and reinforcing the principles of precision agriculture

References

.

Published

2026-09-29