Scanpath
- Abstract
The scanpath eye movement is an essential part in human vision.
The scanpath theory explains that
an internal cognitive model in human brain
controls a top-down active looking and bottom-up perception.
We have been studying how the scanpath changes
as a function of class of image observed by human.
We have obtained the human visual regions-of-interests,
hROIs, by psychophysical experiments; and compared
them using the positional similarity index, Sp.
We have also tried to find how the predictability
of the hROIs by image processing algorithms, IPAs,
can change on the scanpath.
We have compared algorithmic regions-of-interest, aROIs,
which are generated by the IPAs, with the hROIs for image classes.
- Pictures used in the experiments
- Publications and Presentations
- Toyomi Fujita, Claudio M. Privitera, Lawrence W. Stark,
"Image-type dependent eigen-Regions-of-interest define conspicuity operators for predicting human scanpath fixation",
Computers in Biology and Medicine, Volume 37 Issue 7 pp.965-974 (July 2007).
[DOI ]
- Claudio M. Privitera, Orazio Gallo, Giorgio Grimoldi,
Toyomi Fujita, Lawrence W. Stark, "Combining conspicuity maps for hROIs
prediction", 2nd International Workshop on Attention and Performance
in Computational Vision (WAPCV 2004), pp.104-111, 2004.
[PDF File ]