Here, we define correspondence points between me and George Clooney. There are 50 correspondence points on total to map the eyebrows, eyes, nose, mouth, face, and corners of each image.
I then created a Dalauney triangulation of the mean of the correspondence points.
To compute the "Mid-Way" face of an image, we repeat the following process for each triangle in the mean shape triangulation:
To compute the Morph Sequence face of an image, we use the same algorithm that we used to generate the "Mid-Way"
face for 45 different values of alpha between [0, 1]. alpha is a variable that controls the extent of both shape warping and cross-dissolve.
In this part, we take a bunch of Danish faces and their pre-labeled correspondence points and average them to get a mean shape. Below are 12 Danish faces that were warped to the mean Danish face.
We find the mean Danish face by averaging all of the warped faces. A surprisingly good result!!
It is what it is ...
Honestly not too bad!!
Here, I create caricatures of myself by extrapolating from the mean Danish face.
The caricature shape is found by adding a scaled (alpha > 1) difference between the average Danish face and my face.
Larger alpha implies greater extrapolation.
I was inspired by the Snapchat gender swap filter and wanted to reproduce the results
I will apologize here in advanced for what you are about to witness.
This clearly does not look as good as Snapchat's filter, perhaps this is why they won't hire me :(
In this section, a few of my classmates and I banded together to create a face morphing music video! Here, I only include the morph from me to Avni.
Link to class morph video: (https://drive.google.com/file/d/1Pogeg2JmzhZe9SCgvKohIc31DNvk-4fp/view?usp=sharing)