thebhrugubanda / mq-comp8240-major-project-group-h Goto Github PK

To reproduce the same results, the dataset needs to be downloaded using this form by agreeing to their terms & conditions.

Repository Descprition:
This repostitory is a major project ,part of the course unit COMP8240 - Applications of Data Science

1. Sai Diwakar Bhrugubanda (45852189)
2. Saiprudhvi Meda (45725535)
3. Rahul Sonkusare (45779880)
4. Shruti Tyagi (45831815)

There are two main stages of implemenation

1. Replication of original work
2. Creating new data & applying on the original work

Dataset used: link

• Data Extraction
• Using the script to download
python download-Faceforensics.py -d all -c c23 -t videos
• Using the script to extract frames from the videos downloaded.
python extracted_compressed_videos.py -d <"all" or single dataset via "Face2Face" or "original"> -c c23
• Data Pre-Processing

File: Original Work/ Data Pre-Processing.ipynb

• First faces are extracted from video frames using bounding boxes.
• Splitting the data and creating Train,Test and CV data.
• Shuffling the data and assigning class labels to every image 1 or 0 (Fake =1 and Real =0).
• Pickling the data to create .pkl files.
• Xception Modelling

File: Original Work/ Xceptionnet_Modelling.ipynb

• Import the pre-processed data i.e. Pickle files.
• Feed it into the model to pre-train and then test the accuracies using 2 variation of epochs.
• Evaluate the model on Train,CV and Test data to find accuracy of the model.

• Creating New Data
1. First Order Motion for images animation (Deep fakes) Source Github

File: New Data/Creating-Deepfakes.ipynb

Since the model is performing too well and creating perfect deepfakes, to test the XceptionNet model accuracy we are creating two types of deepfake videos.

1. Deepfakes based on front facing images which create perfect deepfakes.
2. Deepfakes based on side angle images which create deepfakes that are little easy to differentiate between fake and real.
2. Acquired faceswap and face2face from thirdparty sources i.e youtube
• Xception Modelling

File: New Data/ Xceptionnet_Modelling(Front Facing Data).ipynb

File: New Data/ Xceptionnet_Modelling(Side Facing Data).ipynb

Application of XceptionNet of 2 Variations of data i.e Front-Facing and 2. Side-Facing images

1. Rössler, Andreas & Cozzolino, Davide & Verdoliva, Luisa & Riess, Christian & Thies, Justus & Nießner, Matthias. (2019). FaceForensics++: Learning to Detect Manipulated Facial Images.
2. Siarohin, Aliaksandr & Lathuilière, Stéphane & Tulyakov, Sergey & Ricci, Elisa & Sebe, Nicu. (2020). First Order Motion Model for Image Animation.