Automated Apple Tree Disease Classification System 🍎

This project develops an automated system for classifying apple tree diseases using advanced Deep Learning techniques. Its core objective is to provide farmers and agronomists with a reliable diagnostic tool to quickly identify diseases from images of apple leaves.

Project Objectives

• Classify Apple Leaf Images: Categorize images into predefined states: Apple Scab, Cedar Apple Rust, and Healthy.

Key System Components

• Core Technology: Utilizes a Modified EfficientNetV1 deep learning architecture. This lightweight model offers strong generalization capabilities and represents a significant research contribution. 🧠
• Data Handling: Involves crucial preprocessing steps like data augmentation to expand the dataset and normalization to standardize image inputs for effective model training.
• Model Evaluation: Rigorously evaluates the model using Accuracy, Precision, Recall, and F1-score, tested against a distinct evaluation dataset.
• Validation: Implements K-Fold Cross-Validation to ensure robust and stable model performance.

Scientific Contribution & Documentation 🔬

This repository serves as the official hub for the peer-reviewed paper: "Classification of Apple Leaf Diseases Using a Modified EfficientNet." It also includes related presentation slides and official certificates acknowledging the project team as Authors and Speakers.