How interesting is this? Finding interest hotspots and ranking images using an MPEG-7 visual attention model
Wolf, Heiko; Deng, Da
Cite this item:
Wolf, H., & Deng, D. (2005). How interesting is this? Finding interest hotspots and ranking images using an MPEG-7 visual attention model (pp. 67–76). Presented at the 17th Annual Colloquium of the Spatial Information Research Centre (SIRC 2005: A Spatio-temporal Workshop).
Permanent link to OUR Archive version:
http://hdl.handle.net/10523/697
Abstract:
A lively Dunedin street scene, and a panoramic view of the Southern Alps - two images that might appeal and interest a viewer. But where do people look, and which of those images appears more interesting? In this paper, we are introducing a visual attention model based on MPEG-7 descriptors that creates multi-scale feature maps to detect interest hotspots in images. Further, we are assessing three methods that use attention models for image ranking and compare them to results gathered in a user test. Preliminary results indicate that rankings created by our model show a high agreement with rankings obtained in a pilot user study.
Date:
2005-11
Conference:
17th Annual Colloquium of the Spatial Information Research Centre (SIRC 2005: A Spatio-temporal Workshop), Dunedin, New Zealand
Keywords:
Visual attention model; visual saliency; scene analysis; image ranking; MPEG-7
Research Type:
Conference or Workshop Item (Paper)