Title:	A PROBABILITY-BASED METRIC FOR RAPID RETRIEVAL OF EYE-GAZE DISTRIBUTION DATA
Author(s):	Daisuke Sakurai, Shigeo Takahashi
ISBN:	978-972-8939-74-8
Editors:	Yingcai Xiao
Year:	2012
Edition:	Single
Keywords:	Data retrieval, eye-tracking data, distributions of eye-gaze fixations, probability-based metrics.
Type:	Short Paper
First Page:	152
Last Page:	156
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	In this paper, we present a novel method for rapidly retrieving eye-gaze distributions that are similar to the user input. When analyzing images such as artistic paintings and photographs, the corresponding distributions of eye-gaze fixations provide useful information about the salient features embedded in the target images. Nonetheless, due to the lack of appropriate models for representing uncertainties in eye-gaze distributions, conventional retrieval techniques based on image processing do not fully allow us to identify similar distributions, and thus usually lead to time-consuming side-by-side visual comparison between eye-gaze fixation distributions that is error-prone. For facilitating such data retrieval, we introduce a probability-based metric together with a search algorithm for the distributions of eye-gaze fixations. The effectiveness of the proposed method has been tested through a user study, in which we compared the results by our system with those obtained through a user study.
	Go Back