Privacy preserving using face replacement-based image anonymisation tool

Bachelor's Thesis in University of Tartu

Requirements

• OpenCV
• DLib
• Numpy
• Imutils
• Scipy

Average Face

How to run

On the final line of code, in the function "Averager" change the directory name to a folder that contains all images that you want to average and run the python code

averager(list_imgpaths('<Directory Name Here>'))

Run the code by giving the command python average_face.py after changing the name of directory in code.

Face Swap

How to run

On the final line of code, in the function "Averager" change the directory name to a folder that contains all images that you want to average and run the python code

base_face = cv2.imread('<Insert Input Image Name Here>', cv2.IMREAD_COLOR)

If you want to change the name of output file, edit the line

cv2.imwrite("<Insert Output Image Name Here>", faces_swap)

Run the code by giving the command python face_swap.py after changing the name of directory in code.

Student

Maris Popens

Supervisors

Doğuş Karabulut

Professor, Dr. Gholamreza Anbarjafari

UNIVERSITY OF TARTU

Faculty of Science and Technology

Institute of Technology