Introduction

A morph is a simultaneous warp of the image shape and a cross-dissolve of the image colors. In this project, I will produce a "morph" animation of my face into someone else's face, compute the mean of a population of faces and extrapolate from a population mean to create a caricature of myself.

Part 1 The Morph Sequence

In the first part, I will produce an animation of Scott's face into Kim Jong-un's face. The approach is divided into several steps. First of all, I show the images of Scott and Kim, and pick correspondence points on both of their face. Then I do triangulation on the first image's points. Next, I calculate the mid-way face with the shapes of two faces, and I morph both faces to the mid-way face by warp each pair of corresponding triangles.

Now, let's see...

Part 2 The Mean Face of a Population

In this part, I will calculate the mean face of Brazilian face, and then morph two normal Brazilian faces to the mean face. In the end, I will show what happens when Scott's face meet Brazilian mean face.

Now, let's morph a Brazilian man and a Brazilian woman to the mean face.

Now, let's see what happens when Scott's face meet Brazilian mean face.

Part 3 Carricature

In this part, I will show you a more Brazilian Scott and a less Brazilian Scott by extrapolating from the mean. The first image has an extrapolating parameter of 0.8, the second one has -0.5. As we can see, Scott is much thinner than the mean Brazilian face.

Bells and Whistles: Change of Ethinity

In this part, I will invite my friend Will, by using the average Indian face I found online, I will be able to generate a more Indian looking Will.