In this project, I created morphs of face images, including myself. A morph is a simultaneous warp of the image shape and a cross-dissolve of the image colors. The warp is done by using corresponding points of the images so that the transition is smooth. In addition, this project also creates a mean face of a population of faces, and uses warping to create caricatures.
In creating the mid-way face, I used the algorithm described in the project spec. This includes 1) computing the average shape using points 2) warping both faces into those points 3) averaging the colors together. To do this, I implemented the compute_affine function for the triangle points.
Using the warp functions created earlier, I created a morph function. The input images are first warped into an intermediate shape configuration controlled by a warp fraction, and then cross-dissolved according to another fraction. Afterwards, a gif is created by compiling images of each frame of a different fraction.
The population I used was a subset of the Danes dataset. For each face, they were morphed into the average shape. I took a specific example from the data set and showed its warp into the average shape. Afterwards, I warped my face into the average geometry and the average face to my geometry.
Here, I produced a caricature of your face by extrapolating from the population mean I calculated in the last step.
For this Bells and Whistles, I focused on the change of age. I morphed the appearance in a sequence and included the midway face (it looks like a teenager).