Department of Computer Science
Incorporating concept ontology into multi-level image indexing
The huge availability of multimedia data in the World Wide Web, and its exponential growth from the past few years, has made the search, indexing and maintenance of the information a difficult and time consuming task when they are carried out manually. Image indexing becomes one of the most popular research topic as the effectiveness of image retrieval depends on meaningful indexing. In this paper, we propose an extension of image annotation models which incorporaties concept ontology for multi-level image indexing. Our system is evaluated quantitatively using more than 100,000 web images and around 1,000,000 tags. Experimental results indicate that this approach is able to deliver good results. Copyright 2009 ACM.
Automatic semantic annotation, Concept-base image annotation, Image retrieval
Source Publication Title
ICIMCS '09 Proceedings of the First International Conference on Internet Multimedia Computing and Service
Link to Publisher's Edition
Wong, R. C F, and C. H C Leung. "Incorporating concept ontology into multi-level image indexing." ICIMCS '09 Proceedings of the First International Conference on Internet Multimedia Computing and Service (2009): 90-96.