EyeVisionBot (2003)

Hans H. Diebner
Sebastian Fischer
Lasse Scherffig

Work Description

Objectives of the project are, on the one hand side, to optimize image retrieval from databases and the Internet with the aid of eye tracking and adaptive algorithms, and, on the other hand, to critically scrutinize algorithms and information technology with respect to instrumentalization.
As a start, EyeVisionBot presents 9 to 25 images (depending on the size of the monitor or the projection screen). The time that the gaze dwells on the individual image is registered via eye tracking. The cumulated viewing times are used to estimate the searched category. By-and-by a new set of images are requested based on keywords which are generated from the previous searching behaviour. In addition, structural comparisons with the so far longest viewed images are performed.
Keywords and structural attributes can be used for the search. The efficiency of the keyword-based search in databases depends on the usefulness of the classification and the correct assignment of the images to the categories. In the world wide web the keywords address terms that appear on the web page in which the image is embedded or as image file names. The structural search is based on comparisons of the searched images to structurally resembling archetypes.

EyeVisionBot shall be understood as both an experimental and a critical interface to capture and analyze preconscious perception, too. Therewith, the search and classification behavior is to be investigated eventually in order to optimize the adaptation to the needs of the user. Primarily, however, EyeVisionBot wants to sensitize to an enslaving impact such information technologies may have. This research is not restricted to the derivation and analysis of adaptive algorithms to estimate the desired categories but also comprises the optimization of classifications as well as the presentational interface. We expect new insights with respect to the classification of databases as well as innovations in the fields of adaptive and context sensitive methods.
EyeVisionBot has been realized with the image database of "Media Art Net" and was part of the project "Dynamical cognitive systems, neural networks and perception" of the Institute for Basic Research at the Center for Art and Media (ZKM). It is now further developed at the Institute for New Media (INM), Frankfurt. The prototype was funded by the Land Baden-Württemberg with funds from the "Zukunftsoffensive III für innovative Projekte." [H.H.D.]

[bearbeiten]