Generation of Facial Cartoons

Wai Yin Leung


Supervised by Paul L Rosin; Moderated by Yukun Lai

The aim of this project is to take an input image of a frontal face and generate a cartoon stylised version. Many possible approaches are possible, see e.g.

Data-driven face cartoon stylization, Zhang et al., 2014.

Image Based Hair Segmentation Algorithm for the Application of Automatic Facial Caricature Synthesis, Shen et al., 2014.

At least in the first instance, this project will take a simple approach, in which facial features (eyes, mouth, etc) are matched to a library containing multiple examples of these features. Then the face can be stylized by compositing the matched features, which could be refined by adapting them to better fit the input image.

There are many other aspects that can be considered such as detection of hair, background, facial outline, etc.

Initial Plan (30/01/2017) [Zip Archive]

Final Report (05/05/2017) [Zip Archive]

Publication Form