Digital makeup transfer using machine learning algorithms

Abstract

As the world becomes more and more interconnected, social media has become a popular way for people to share their lives and connect with others. Posting self-portraitures have become increasingly popular on social media platforms, leading to a rise in demand for photo-editing applications as a way to beautify their self-portraits. However, current applications available for photo editing are designed solely for raster images, which can result in a loss in image quality when resized.

Hence, this project presents the design and implementation of a digital makeup transfer algorithm using machine learning algorithms which will allow users to apply makeup to their portrait images digitally. This project aims to develop a makeup transfer algorithm that edits vector graphics such that image quality is maintained. Different colour transfer methods and facial segmentation models will also be examined and further discussed in this project