Title :
Image Content Annotation Based on Visual Features
Author :
Ye, Lei ; Ogunbona, Philip ; Wang, Jianqiang
Author_Institution :
Sch. of Inf. Technol. & Comput. Sci., Wollongong Univ., NSW
Abstract :
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 categorization using MPEG-7 VCE2 dataset and its ground truth. The experimental results show a promising performance
Keywords :
Bayes methods; content-based retrieval; data compression; image classification; image retrieval; inference mechanisms; Bayesian inference; MPEG-7 VCE2 dataset; atomic concept space; automatic image content annotation technique; collective concept space; feature classification; photo categorization; structural visual feature; Bayesian methods; Cities and towns; Hidden Markov models; Layout; MPEG 7 Standard; Pixel; Space technology; Support vector machine classification; Support vector machines; Testing;
Conference_Titel :
Multimedia, 2006. ISM'06. Eighth IEEE International Symposium on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7695-2746-9
DOI :
10.1109/ISM.2006.89
