A hybrid ontology and visual-based retrieval model for cultural heritage multimedia collections

This paper introduces a hybrid multimedia retrieval model that is capable of retrieving cultural heritage multimedia content, based on their semantic annotation with the help of an ontology and on low level visual features with a view to finding similar content. The main novelty is the way in which these techniques cooperate transparently during the evaluation of a single query in a hybrid fashion, making recommendations to the user. A search engine has been developed implementing this model, which is capable of searching through cultural heritage multimedia collections, and indicative examples are discussed, along with insights into its performance.