Half a Life in 2 Minutes
For more than 21 years, Noah Kalina has taken a photograph of himself. Periodically, he makes video compilations of the photos — you’ve probably seen them here or elsewhere. For his latest video, he’s collaborated with Michael Notter (visuals) and Paul O’Mara (sound) on a video called 7777 Days.
In a first step, Michael used the machine learning library dlib (http://dlib.net/) and some custom Python code to detected in each of Noah’s photos 5 face landmarks (i.e. both eyes, the nose and the two corners of the mouth). These landmarks were then used to align the faces in all photos, so that the eyes and corner of the mouth were horizontally oriented and always an equal distance apart. After that, some small image intensity correction were applied to make very dark images a bit brighter and very bright ones a bit darker. This was followed by an upscaling of all images (where needed) to a 4K resolution.
The result is a 2-minute video (reminiscent of Jason Salavon’s work) that spans half of Kalina’s life — in the video he ages 2 months every second and 10 years a minute.
Update: Kalina and Notter explain how this video came about and how it was made.
Stay Connected