A Study on Relational Semantic Video Content Extraction Using Bayesian Network Classifier

Abstract

Multimedia data mining is an emergent field, which consists of image mining, video data mining etc. The content based extraction in videos is an important application due to the rapid growth in the video based application. Semantic content is the high level concepts that is the objects and events, for example in a basketball game, the player, a ball are all consider to be an object and the actions takes place throughout the game is consider to be the events. In concept extraction the events and objects are extracted, and it is not that much efficient for the user because the relationship between the objects are missing. Therefore the Bayesian network classifier is used to extract the relationship between the objects. It allows the user to extract the semantic video content more efficiently. The Bayesian network classifier uses an ontology which includes the construction of domain ontology. The VISCOM is used to construct ontology for a given domain and the rule based model is used to define some complex situation more effectively. Using Bayesian Network Classifier improves the extraction process by providing the semantic content with relation between the object. Index terms: Multimedia mining, Video data mining, Semantic content, Domain ontology, Bayesian network classifier.