An app for car detection using traditional machine learning algorithms (SVM)
A simple car detection model that identifies cars in an image by primarily extracting HOG (Histogram of Oriented Gradients) features. The model classifies whether the image contains cars, highlights the detected cars, and provides their positions in the image. It uses traditional machine learning algorithms and a Python script to simulate object detection techniques used in more advanced projects. This mini project was part of an Image Processing course to practice the course content.
- Multiple cars detection.
- Accurate object detection of cars.
- Simple interface to allow users to test the model.
- Clone the repository to your local machine:
git clone https://github.com/mohammedshady/car-detection.git - Navigate to the server directory:
cd backend - Install the required dependencies in the requriements.txt:
pip install -r requirements.txt - Start the Flask server:
python app.py
- Navigate to the client directory:
cd car-detection - Install the required dependencies:
npm install - Start the React development server:
npm run dev - Access the application in your web browser at
http://localhost:5173.
Further improvments include :
- Remove unnecessary code that was used for testing different features.
- Oversample dataset to detect cars from all angles instead of (rear + side) view only.
- Enhance the user interface for improved usability and design.
- Optimize code for faster and easier detection.
- Mohammed Shady - GitHub Profile: mohammedshady | Email: [email protected]
If you encounter any issues or have suggestions for improvements, please reach out via email. Your feedback is valuable and helps us enhance the app for everyone.