VIG-Track Dataset

Human intention is an internal, mental characterization for acquiring desired information. Frominteractive interfaces, containing either textual or graphical information, intention to perceive desiredinformation is subjective and strongly connected with eye gaze. In this work, we determine such intention byanalyzing real-time eye gaze data with a low-cost regular webcam. We extracted unique features (e.g.,Fixation Count, Eye Movement Ratio) from the eye gaze data of 31 participants to generate the datasetcontaining 124 samples of visual intention for perceiving textual or graphical information, labeled as eitherTEXT or IMAGE, having 48.39% and 51.61% distribution, respectively. Using this dataset, we analyzed 5classifiers, including Support Vector Machine (SVM) (Accuracy: 90.13%).