Developed an AI-powered plant disease detection system as a Computer Vision graduation project during the NTI training program.
The system uses DenseNet121 with Transfer Learning and Fine-Tuning to classify plant leaf images into 38 disease and healthy classes.
Key features:
Image preprocessing and data augmentation
DenseNet121-based image classification
Transfer Learning & Fine-Tuning
Class Weights to handle class imbalance
Prediction with Confidence Score
Validation image testing
Interactive Streamlit deployment
GitHub project integration
The project covers the complete workflow from data preprocessing and model training to evaluation and deployment.