Improving eye-tracking calibration accuracy using symbolic regression
Open Access
- 15 March 2019
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 14 (3) , e0213675
Abstract
Eye tracking systems have recently experienced a diversity of novel calibration procedures, including smooth pursuit and vestibulo-ocular reflex based calibrations. These approaches allowed collecting more data compared to the standard 9-point calibration. However, the computation of the mapping function which provides planar gaze positions from pupil features given as input is mostly based on polynomial regressions, and little work has investigated alternative approaches. This paper fills this gap by providing a new calibration computation method based on symbolic regression. Instead of making prior assumptions on the polynomial transfer function between input and output records, symbolic regression seeks an optimal model among different types of functions and their combinations. This approach offers an interesting perspective in terms of flexibility and accuracy. Therefore, we designed two experiments in which we collected ground truth data to compare vestibulo-ocular and smooth pursuit calibrations based on symbolic regression, both using a marker or a finger as a target, resulting in four different calibrations. As a result, we improved calibration accuracy by more than 30%, with reasonable extra computation time.Keywords
This publication has 43 references indexed in Scilit:
- Orbits2015
- Pupil2014
- Pursuit calibration2013
- Pursuits2013
- The influence of calibration method and eye physiology on eyetracking data qualityBehavior Research Methods, 2012
- Study of Polynomial Mapping Functions in Video-Oculography Eye TrackersACM Transactions on Computer-Human Interaction, 2012
- Optimization of Gaussian Process Models with Evolutionary Algorithms2011
- Symbolic and numerical regression: experiments and applicationsInformation Sciences, 2003
- Symbolic regression via genetic programming2002
- Using Symbolic Regression to Infer Strategies from Experimental Data2002