This project utilizes Convolutional Neural Networks (CNN) for plant leaf disease detection, employing image processing techniques, feature extraction, and selection. The classification algorithm employed enhances the accuracy of disease identification.
-
CNN Architecture: Implemented a robust CNN architecture for effective feature extraction from plant leaf images.
-
Image Processing: Utilized advanced image processing techniques to enhance the quality and clarity of input images, aiding in accurate disease identification.
-
Feature Extraction and Selection: Extracted relevant features from plant leaf images and employed feature selection techniques to optimize the model's performance.
-
Classification Algorithm: Integrated a powerful classification algorithm to accurately identify and classify plant diseases based on the extracted features.
- Python 3.x
- TensorFlow
- Keras
- OpenCV
- NumPy
- Scikit-learn
- Install the required dependencies using
pip install -r requirements.txt
. - Train the model using the provided dataset by running
train_model.py
. - Test the trained model on new images using
predict.py
.
The project uses a curated dataset of plant leaf images with labeled disease categories. The dataset is available at [link_to_dataset].
Our model achieved 93 % accuracy on the test set, showcasing its effectiveness in plant disease detection.