DeepFake Detection is a machine learning project designed to detect and classify deepfake videos. It leverages deep learning models such as CNN+LSTM and XceptionNet to analyze video frames and identify manipulated content.
- Video Preprocessing: Extracts frames from videos for model input.
- Deep Learning Models:
- CNN+LSTM for temporal video analysis.
- XceptionNet for image classification on extracted frames.
- Dataset Handling: Supports processing and augmentation of video datasets.
- Evaluation and Analysis: Provides performance metrics and insights.
To set up the project on your local machine:
- Clone the Repository
git clone https://github.com/AnuBaluguri/DeepFake-Detection.git cd DeepFake-Detection - Set Up a Virtual Environment
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
- Install Dependencies
pip install numpy pandas opencv-python tensorflow keras matplotlib
-
Run Jupyter Notebook
jupyter notebook
-
Open and Execute a Notebook
• Preprocessing Video Data python
# Run the PreprocessingForVideos.ipynb notebook to extract frames from videos• Train CNN+LSTM Model python
# Open CNN+LSTM.ipynb and run all cells to train the model• Train XceptionNet Model python
# Open XceptionNet.ipynb and execute to train the Xception-based model
DeepFake-Detection/
│── PreprocessingForVideos.ipynb # Preprocessing video data
│── CNN+LSTM.ipynb # CNN+LSTM model implementation
│── XceptionNet.ipynb # XceptionNet model implementation
│── Report.docx # Project report and findings
│── README.md # Project documentation
Ensure the following dependencies are installed:
• Python 3.6+
• NumPy
• Pandas
• OpenCV
• TensorFlow / Keras
• Matplotlib
Contributions are welcome! Follow these steps:
- Fork the repository.
- Create a feature branch:
git checkout -b feature/new-feature
- Commit your changes:
git commit -m "Add new feature" - Push to your branch:
git push origin feature/new-feature
- Open a pull request.
This project is licensed under the MIT License. See the LICENSE file for details.