Semantic Information Extraction of Video Using Ontology
Jie Ma · Journal of Chinese Computer Systems · 2008
With the growing of video data volume, the demand for video retrieval and video semantic information extraction grows as well. In this paper, a new ontology-based composite concept extraction method is proposed, which adopts Bayesian network to construct the ontology and uses the inference rules to perform the composite concept detection providing the atomic concepts in a segment of video. This method analyzes the video content through semantics and constructs ontology to express the hierarchical relationship between the concepts, which narrows the Semantic Gap and achieves good performance in abstract concepts extraction.