Anatomical biometric recognition is widely used in a large number of civilian and government applications, within well-tested biometric parameters. New sensors and matching algorithms have led to the deployment of soft biometrics, which may provide a fast and reliable identity finding procedure. These traits are physical or behavioral human characteristics like skin color, eye color, and gait, used by humans to recognize their peers, presenting distinctiveness and permanence to identify an individual uniquely and reliably. This paper regards a novel Gaze ANalysis Technique, namely GANT, exploiting a graph-based representation of fixation points obtained by an eye tracker during human computer interaction. The main goal is to demonstrate the conjecture that the way an individual looks at an image might be a personal distinctive feature, i.e. a soft biometric application. A novel dataset acquired through the Tobii 1750 remote eye tracker has been used to demonstrate GANT accuracy in soft biometry, in terms of Receiver Operating Characteristic Curve (ROC), Equal Error Rate (EER) and Cumulative Match Curve (CMC).