Face Morphing

Overview

In this assignment I produce a "morph" animation of my face into my favorite Chinese female idol, Yu Yan's face, compute the mean of a population of faces and extrapolate from a population mean to create a caricature of myself. For the Bells and Whistles, I tried changing the gender of myself and collaborated with a group of other students to create a face-morphing music video.

Defining Correspondences

The first step is to define pairs of corresponding points on the two images by hand. Then I create a triangulation of the average of these two sets of points.

Computing the "Mid-way Face"

Before computing the whole morph sequence, I first compute the mid-way face of these two images.

• Computing the average shape (a.k.a the average of each keypoint location in the two faces);
• Warping both faces into that shape;
• Averaging the colors together;

The Morph Sequence

Then I write a morph function to produce the morph sequence from the original image to the target image. To achieve this, I choose 45 difference values between 0 and 1 as the warp fraction and dissolve fraction to create 45 images. And then I put them together to create the morph gif.

The "Mean face" of a population

In this problem, I took some images from the FEI Face Database and,

• Compute the average face shape of the whole population;
• Morph each of the faces in the dataset into the average shape;
• Compute the average face of the population;

Some Examples:

Caricatures: Extrapolating from the mean

In this part, I create a caricature of myself by extrapolating from the population mean calculated in the last step.

Bells and Whistles

Change my gender

In this part, I find an average image of Chinese male and try morphing my image into it.