Publication

Abstract : Semantic based video/image retrieval is a most critical issue in the multimedia search enginerelated research. Multimedia content annotation improves the accuracy of semantic based content retrieval system where multimedia content annotation can be done in two ways: One is content based annotation and another is context based annotation. The content based annotation of images and videos consist of both low level and high level features which would be derived from the detailed pixel intensity information of images whereas context information would provide the semantic details about the images/videos. In this analysis work, discussion about the various techniques used to retrieve the multimedia content from the web engines with the semantic knowledge awareness is provided. The various research methods that intend to perform the annotation on multimedia contents is discussed in detailed. And also, this analysis work provides the discussion about the techniques in terms of their merits and demerits. Finally this work also provides the numerical evaluation of eachtechnique based on their accuracy in the videoretrieval outcome. The overall evaluation of the surveyed methodologies is performed and provides discussion about the outcome obtained from each technique.