The Community for Technology Leaders
Eighth IEEE International Symposium on Multimedia (ISM'06) (2006)
San Diego, CA
Dec. 11, 2006 to Dec. 13, 2006
ISBN: 0-7695-2746-9
pp: 62-69
Lei Ye , University of Wollongong, Australia
Philip Ogunbona , University of Wollongong, Australia
Jianqiang Wang , University of Wollongong, Australia
Automatic image content annotation techniques attempt to explore structural visual features of images that describe image content and associate them with image semantics. In this paper, two types of concept spaces, atomic concept and collective concept spaces, are defined and the annotation problems in those spaces are formulated as feature classification and Bayesian inference, respectively. A scheme of image content annotation in this framework is presented and evaluated as an application of photo categorisation using MPEG-7 VCE2 dataset and its ground truth. The experimental results show a promising performance.

L. Ye, P. Ogunbona and J. Wang, "Image Content Annotation Based on Visual Features," Eighth IEEE International Symposium on Multimedia (ISM'06)(ISM), San Diego, CA, 2006, pp. 62-69.
94 ms
(Ver 3.3 (11022016))