Improving Statistical Multimedia Information Retrieval Model by using Ontology
This work addresses the semantic gap in multimedia information retrieval for users, but appears incremental as it builds on existing ontology-based approaches.
The paper tackles the problem of matching user queries with available web content in information retrieval systems by using ontology to represent extracted terms as a network graph, and reports that the proposed model reduces the semantic gap and satisfies user needs efficiently.
A typical IR system that delivers and stores information is affected by problem of matching between user query and available content on web. Use of Ontology represents the extracted terms in form of network graph consisting of nodes, edges, index terms etc. The above mentioned IR approaches provide relevance thus satisfying users query. The paper also emphasis on analyzing multimedia documents and performs calculation for extracted terms using different statistical formulas. The proposed model developed reduces semantic gap and satisfies user needs efficiently.