I very much believe in interdisciplinary things, where different fields of knowledge can blend together to create something unique. Since my daughter loves art, and I love technology — I often look into the intersection of those two areas, or so-called Science Art.
PeopleBlending is a technique where we blend several pictures of a face together, aligning them to the eyes, and thus creating a blended, averaged face.
Cognitive Portrait is the continuation of the PeopleBlending idea, where we continue to explore automatic generation of pictures from photographs, taking into account facial landmarks and some other facial features that can be extracted using neural networks.
Art of the Artificial
Art of the Artificial is an exhibition that shows the process of creative machine learning, i.e. how a computer gradually learns to create paintings and produce text, looking at samples produced by humans. For training images, we used portraits and flower paintings from WikiArt, and for text - Russian fairly tales and Chekhov prose.
Together with my daughter we have created a series of art objects that show time. Those object were presented at Moscow Maker Faire, and got a 3rd place award at a conference “Start into Science”.