A visual interactive environment for image retrieval by subjective parameters

Recently, in designing computing systems, much focus has been given to support the user´s subjectivity (Kansei in Japanese), by providing the system with a mostly explicit user model. We argue against this explicit nature of the model since there is evidence in neuroscience that the human brain does not have monolithic control and static internal models. We suggest that the user model should rather emerge from a prolonged interaction between the user and the system. We describe our interactive visual environment dedicated to image retrieval based on subjective parameters. It is endowed with a learning agent and an active interface allowing multi-model interaction between the user and the system. This interaction takes the form of symbols, examples or externalization of internal processes