CS180-Project3

Part 2. Computing the "Mid-way Face"

Here are my steps to compute the mid-way of two people:

1. Compute the average shape
2. warping both faces into that shape
3. averaging the colors together. (cross-dissolve)

Part 3. The Morph Sequence

For this part, I setup a range of weights in [0, 1] and I created a morph sequence 45 frames, with duration of 30 ms per frame.

Part 4. The "Mean face" of a population

For this part, I use the iamges from FEI database which is part one that contains images of 200 individuals taken at the Artificial Intelligence Laboratory of FEI in São Bernardo do Campo, São Paulo, Brazil.

I seperated the iamges as neutral and smiling. I used the both images to compute the mean face of the population. Also, besides the original points that are provided, I added some more points to make the result better.

Here are some examples of the face that I use to compute the mean face:

Here are the steps to compute the mean face of a population:

1. Compute the average face shape of the whole population or some subset of the population
2. Morph each of the faces in the dataset into the average shape
3. Compute the average face of the population and display it.

Here is my face warped into the average geometry, and the average face warped into my face’s geometry.

Part 5. Caricatures: Extrapolating from the mean

Here, the formula I used is: avg_img + apha * (my_img - avg_img), where apha is 1.5

Bells and Whistles