Banana Leaf Disease Detection CNN Train Flask in Python Projects

Banana Leaf Disease Detection CNN Train Flask in Python Projects
Abstract
Banana is one of the most widely consumed fruits globally, and its cultivation is highly affected by various leaf diseases such as Black Sigatoka, Banana Bunchy Top Virus, and Panama Disease. Early detection of these diseases is crucial to preventing crop loss and ensuring sustainable yield. This project, Banana Leaf Disease Detection using CNN trained with Flask Deployment in Python, proposes a computer vision–based approach to identify and classify banana leaf diseases from captured images. A Convolutional Neural Network (CNN) model is trained on a dataset of healthy and diseased banana leaf images. The trained model is then integrated into a Flask web application, enabling farmers and agricultural researchers to upload leaf images and receive instant predictions. The project utilizes Python libraries such as TensorFlow/Keras, OpenCV, NumPy, Matplotlib, and Flask to build an accurate, scalable, and user-friendly system.

Existing System
Currently, banana leaf disease detection largely depends on manual inspection by agricultural experts. This process is time-consuming, costly, and prone to human error, especially in large farms. Some existing digital approaches use basic image processing techniques like color thresholding and edge detection, but they struggle with variations in lighting, background noise, and overlapping disease symptoms. Moreover, most existing systems are not real-time or farmer-accessible, as they lack deployment in user-friendly platforms such as mobile or web applications. This makes disease management reactive rather than proactive.

Proposed System

The proposed system introduces an automated CNN-based banana leaf disease detection model trained on a labeled dataset of banana leaf images. The CNN extracts deep features such as leaf texture, color, and pattern to classify images into healthy or diseased categories with high accuracy. After training, the model is integrated into a Flask web application, where users can upload an image of a banana leaf, and the system instantly predicts its health status. The application provides a simple and interactive interface that makes it usable even for non-technical users such as farmers. Compared to existing methods, this approach ensures higher accuracy, real-time detection, scalability, and accessibility, helping in early disease diagnosis and better crop management.

Customer Reviews (0)

Share Your Experience

Rating

Your Comment

Submit Review Cancel

No reviews yet. Be the first!