Skip to content

NoorMahammad-S/DeepFake_Detection_using_Convolutional_Neural_Networks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 

Repository files navigation

AI & ML Project

DeepFake Detection using Convolutional Neural Networks

This repository contains the source code and documentation for a DeepFake detection project. The project leverages machine learning techniques, specifically a convolutional neural network (CNN) based on the MobileNetV2 architecture, to identify and distinguish between authentic and manipulated images.

Key Features

  • Data Loading and Preprocessing: Real and DeepFake images are loaded and preprocessed using OpenCV, ensuring a standardized format for analysis.
  • Data Augmentation: ImageDataGenerator is employed for on-the-fly data augmentation during training to enhance model generalization.
  • Model Architecture: MobileNetV2 is used as the base model for feature extraction. The custom neural network includes global average pooling, dense layers, dropout for regularization, and a sigmoid layer for binary classification.
  • Training and Evaluation: The model is trained using TensorFlow, and rigorous evaluations are conducted on a separate testing dataset to assess performance.
  • Model Persistence: The trained model is saved for future use, facilitating deployment for real-time DeepFake detection.

Getting Started

Prerequisites

  • Python 3.x
  • TensorFlow
  • OpenCV
  • Other dependencies (install using pip install -r requirements.txt)

Installation

  1. Clone the repository:

    git clone https://github.com/NoorMahammad-S/deepfake-detection.git
    cd deepfake-detection
  2. Install dependencies:

    pip install -r requirements.txt
  3. Run the project:

    python your_main_script.py

Usage

  1. Customize the paths to your real and DeepFake image datasets in your_main_script.py.
  2. Run the script to train the model and save it for future use.
  3. Experiment with different hyperparameters and model architectures for potential improvements.

Contact

About

This project employs artificial intelligence (AI) techniques, specifically machine learning (ML), to address the challenge of detecting DeepFake images. DeepFakes are synthetic media that use deep learning algorithms to manipulate or generate realistic-looking content, often involving human faces.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages