Skip to content

Latest commit

 

History

History
95 lines (83 loc) · 3.45 KB

README.md

File metadata and controls

95 lines (83 loc) · 3.45 KB
Raw

iDentify: Dental Anomaly Detection using YOLOv9 with Data Augmentation

Overview

iDentify is a web-based application designed to facilitate the detection and classification of dental anomalies from panoramic X-rays. The tool consists of two main components: a React Vite-based front-end application and a backend system incorporating a trained YOLOv9-c model wrapped in a FastAPI container.

Inference on Panoramic X-ray

Features

Front-End

The frontend is built using React Vite, a modern web development framework that allows for efficient and scalable development. The application offers several functionalities, including:

  • Welcome page
  • Sign-up and login (using Firebase Authentication)
  • Dashboard for image upload, result viewing, zoom feature, and PDF export with detailed text descriptions of detected dental anomalies
  • Feedback page for model performance feedback

Back-End

The backend is a FastAPI application responsible for:

  • Receiving and processing image data
  • Running the detection algorithm
  • Returning the results along with confidence scores for each classification of dental anomalies (Caries, Deep caries, Periapical lesion, and Impacted tooth)

Setup Instructions

Backend (FastAPI)

You have two options to run the backend:

  1. Using Docker: Pull the Docker image from Docker Hub and run it:

    docker pull kanwalmehreen/identifyapp:latest
docker run -p 8000:8000 kanwalmehreen/identifyapp:latest

  2. Running Locally:

    1. Clone the repository: 
      git clone https://github.com/kawiiii/iDentify.git
cd iDentify/api
    2. Create a virtual environment: 
      python -m venv venv
    3. Activate the virtual environment:
      • On Windows: 
        venv\Scripts\activate
      • On macOS and Linux: 
        source venv/bin/activate
    4. Install dependencies: 
      pip install -r requirements.txt
    5. Download the model from Google Drive and place it in the api/models directory.
    6. Run the backend: 
      uvicorn main:app --reload

You can access the backend at http://0.0.0.0:8000. Press CTRL+C to quit.

Frontend (React Vite)

  1. Clone the repository if you haven't already.
  2. Navigate to the frontend directory: 
    cd iDentify/frontend
  3. Copy the .env.example file to create a new .env file: 
    cp .env.example .env
    Fill in the Firebase keys and any other required environment variables in the newly created .env file.
  4. Install the dependencies: 
    npm install
  5. Install react-modal: 
    npm install react-modal
  6. Run the frontend development server: 
    npm run dev

Once the development server is running, you can access the frontend application at http://localhost:5174/ .

License

This project is licensed under the MIT License. See the LICENSE file for more details.

Contributors