Gaze movement inference for implicit image annotation

An innovative semi-automatic image annotation system is enriched with the feedbacks of user´s eyes. This system implicitly exploits the competence of human mind and it utilizes the computational power of the computers in order to achieve a pervasive and accurate annotation. This method requires minimal user interaction. It makes it suitable to be used in distributed environments while the users are performing their usual daily surfing. The user´s gaze state on the trial screen is monitored and interpreted by an interface promoted by fuzzy inference. The preliminary results indicate that in a multi-user environment the annotating precision of the system is over 80% with the Recall between 60%-80%.