ETCAL – a versatile and extendable library for eye tracker calibration

Eye tracking is an increasingly popular technique that may be used for a variety of applications including user experience analysis, usability engineering and interactive games. Moreover, this technique may be useful inter alia in education, psychological tests and medical diagnosis. Video-based oculography (VOG) is the most commonly utilized technique because it is non-intrusive, can be applied in users' natural environments and is relatively cheap as it uses only basic cameras. There are already well-established methods for eye detection using still images registered by a camera. However, to be usable in the estimation of gaze position, eye image features must be associated with the place where an observer is looking; this typically requires the evaluation of several parameters during a process called calibration. The parameters significantly influence the quality of the analysis of subsequently collected data, thus they should be adjusted to the eye tracker used, the user and the environment. The purpose of this study is to present various calibration techniques and introduce an open, extendable and ready-to-use software application that implements these techniques. This software implements several algorithms already described in the literature and introduces some novel techniques. It provides the opportunity to compare different methods including plug-in self-developed filters and optimization algorithms; it also allows for analysis of results.