Here, I computed the mid-way face between me and my friend. I used 45 points to gather some key features and the general geometry of our faces. Then, I used Delaunay triangulation to create average triangles, warping both our faces and averaging the colors together.
As you can see, my face warped into his has larger eyes and a smaller facial structure, whereas his face warped into mine has smaller eyes and a slightly wider face.
Here is a 45-frame sequence of our faces being morphed into each other. I used a dissolve fraction to cross-dissolve and a warp fraction to warp our faces at different parts of the sequence. These ratios help gather a frame by frame transition to each of the faces.
I took a database of 32 male Danes and computed a mean average geometry of their faces.
I then morphed the mean of 32 male Danes into two of the Danes in the dataset, as shown in the example below.
Here I computed the mean image with my own image, as well as 1) my face warped into the average geometry, and 2) the average face warped into my geometry.
Finally, I created a caricature of different intensities of my face with mean Dane geometry. My eyes definetely got larger, and my forehead also warped into a larger area. The ending result is a very boxy (almost rectangular version of my face) which I'm definetely not used to.
For this portion of the project, I created a themed video of some of the players in this year's NBA Finals. I morphed the different player's faces into each other, and created a long gif sequence. Let's go Miami!
For this portion of the project, I computed the midway face between a baby and an elderly woman, in order to see how I would look at different times in my life.