Face swap algorithm for AI code implementation report
Face swapping refers to the task of swapping faces between images or in a video, while maintaining the rest of the body and environment context. We present our on-going effort of constructing a large-scale benchmark for face forgery detection.
Our project combines the identity information from a source image and attribute information from a target image to generate the final swapped face image.
The main motivation behind this project is the continuous evolution of technology and its use in the field of Forensics, Entertainment and other such fields. We can help this in forgery detection by implementing an efficient algorithm that can generate a huge training and test dataset that can be used to develop DeepFake algorithms.
It has attracted extensive attention in recent years for its broad application prospects in entertainment, privacy protection, and the theatrical industry. Face swapping has both positive applications such as entertainment, human-computer interaction, etc., and negative applications such as DeepFake threats to politics, economics, etc.
Developing a DeepFake photo or video typically involves feeding hundreds or thousands of images into the artificial neural network, “training” it to identify and reconstruct patterns
git clone https://github.com/somya51p/Face_swap.git
cd Face_swap/Face_swap
Create a Virtual Env with Python version 3.7 Install the dependencies with
pip install -r requirements.txt
Then Run the .ipynb files