Medi-Flow is a web application that utilizes transfer learning to identify medicinal plant flowers from user-uploaded images. It employs the powerful DenseNet image classification model to achieve high accuracy in its predictions.
Features
- Plant Identification: Accurately identifies medicinal plant flowers from images.
- Transfer Learning: Leverages transfer learning to optimize the DenseNet model for medicinal plant flower classification.
- Web Interface: Provides a user-friendly web interface for uploading images and viewing predictions.
Requirements
- Python 3.7 or higher
- TensorFlow 2.x
- Streamlit 0.86 or higher
- OpenCV 4.x or higher
- PIL (Python Imaging Library)
Installation
-
Install the required dependencies:
pip install tensorflow streamlit opencv-python pillow
-
Clone the project repository:
git clone https://github.com/majipa007/Medi-Flow-Wiki.git
-
Navigate to the project directory:
cd Medi-Flow-Wiki
Usage
-
Start the Streamlit application:
streamlit run app.py
-
Open the application in your web browser:
http://localhost:8080
-
Upload an image of a medicinal plant flower using the file uploader.
-
The application will process the image and display the predicted flower name along with its confidence score.