What does the artist see that non-artists don't? What aspects of the seen and the unseen yield the essence of creative artistic invention? In the art world where a single, preselected polished work is introduced under the glow of anticipated presentation, the progressive search for that decisive moment displayed is seldom demonstrated. Taking a body of mixed media and photographic work as the initial point of departure to understand idea emergence and resulting representation, I present and discuss the visual stages of my own multidisciplinary creative process while in pursuit of questions and answers about the mind/brain. From literal, spherical, abstract, and squared to soft, harsh, sensual, and reflective, I reveal the explicit and implicit layered connections I make as a polymath Artist-Scientist between disciplines, history, artistic styles, visual perception, emotion, and form – the vast information networks that underlie our human experience.
In recent years, Convolutional Neural Networks (CNNs) have gained huge popularity among computer vision researchers. In this paper, we investigate how features learned by these networks in a supervised manner can be used to define a measure of self-similarity, an image feature that characterizes many images of natural scenes and patterns, and is also associated with images of artworks. Compared to a previously proposed method for measuring self-similarity based on oriented luminance gradients, our approach has two advantages. Firstly, we fully take color into account, an image feature which is crucial for vision. Secondly, by using higher-layer CNN features, we define a measure of selfsimilarity that relies more on image content than on basic local image features, such as luminance gradients.