TY - GEN
T1 - A probability-based metric for rapid retrieval of eye-gaze distribution data
AU - Sakurai, Daisuke
AU - Takahashi, Shigeo
PY - 2012/12/1
Y1 - 2012/12/1
N2 - 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-byside 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.
AB - 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-byside 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.
UR - http://www.scopus.com/inward/record.url?scp=84887277432&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84887277432&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84887277432
SN - 9789728939748
T3 - Proc. of the IADIS Int. Conf. Computer Graphics, Visualization, Computer Vision and Image Processing 2012, CGVCVIP 2012, Part of the IADIS MCCSIS 2012
SP - 152
EP - 156
BT - Proc. of the IADIS Int. Conf. Computer Graphics, Visualization, Computer Vision and Image Processing 2012, CGVCVIP 2012, Part of the IADIS MCCSIS 2012
T2 - IADIS International Conference Computer Graphics, Visualization, Computer Vision and Image Processing 2012, CGVCVIP 2012, Part of the IADIS Multi Conference on Computer Science and Information Systems 2012, MCCSIS 2012
Y2 - 21 July 2012 through 23 July 2012
ER -