Automating the process of gaze tracking data using soft clustering

The aim of the paper is to automate the processing of gaze tracking data through soft clustering techniques. Standard analysis software for eye gaze tracking data requires users to define areas of interest, which may not be best option for exploratory analysis, where users may want to analyze eye gaze tracking data to know the area of interest. We have presented results on using Fuzzy c-means and Expectation Maximization algorithms on gaze tracking data and using an entropy based cluster validation index, we tried to automate identification of areas of interest. In our study, data from search task in digitally rendered 2D architectural plans have been explored and results indicated that irrespective of clustering technique, users fixated attention only 2 or 3 times for individual image. We have also presented GUI of a tool that can automatically identify areas of interest for any gaze tracking data sample using FCM or EM Algorithms.