Aikon II

Sketches, anomymous people, Patrick tresset (by hand), 2000.
Aikon-ii. (2008-2012)Watch the first videos here

Drawing, is the human activity we investigate in the AIKON project. It has been practiced in every civilisation for at least the last 30,000 years. The project will be using computational and robotic technologies to explore the drawing activity. In particular the research focuses on face sketching. What can explain that for a non-draughtsman it proves so difficult to draw what they perceive so clearly, while an artist is able to do so sometimes just with a few lines, in a few seconds? Furthermore, how can an artist draw with an immediately recognisable style/manner? How can a few lines thrown spontaneously on paper be aesthetically pleasing? Art historians, psychologists, neuroscientists --- such as Arnheim, Fry, Gombrich, Leyton, Ramachandran, Ruskin, Willats, Zeki --- have argued that artists perceive the world differently.

Our project will follow two main research paths. One will be based on the study of sketches in archives, notes left by artists and specialists' research. The other path will be based on contemporary scientific and technological knowledge. Even if still partial, the knowledge of our perceptual and other cognitive systems has progressed and advances in computational hardware, computer vision and artificial intelligence, now permits the computational simulation of some perceptual, and cognitive processes. We believe that it is now possible, with some imagination and insights, to implement a coarse computational simulation of the processes active when an artist is sketching faces from life.

The main objective of our investigation is to implement a computational system capable of simulating the various important processes involved in face sketching. The ensemble of processes to be simulated, including; the visual perception the subject and the sketch, the drawing gestures, the cognitive activity: reasoning. the influence of the years of training, etc., the inter-processes information flows. It is evident that due to knowledge and technological limitations the implementation of each process will remain coarse and approximate. The system implemented is expected to draw in its own style.

Diagram of Processes (high level).
AikonII is supported by a Leverhulme Trust 3 year research grant.
Press Release of February 23, 2009.