Content Based Information Retrieval Using Relevance Techniques

Recently, retrieving multimedia content has become an important research area. Content based retrieval in multimedia is a research problem since multimedia data needs detailed interpretation from pixel values. Information Retrieval (IR) can be defined as the activity of providing the user with his/her information need. Sometimes it is not possible to retrieve to the user the exact information they have in mind. The basic idea of relevance feedback is to shift the burden of finding the "Right query formulation" from the user to the system. To enable this feature, the user provides the system with Relevance Feedback. This user feedback typically takes the form of relevance judgments expressed over the resulting set. The "feedback loop" can then be iterated multiple times, until the user gets satisfied with the results. In this paper, techniques to improve relevance feedback in content based searches are discussed and our paper shows how relevance improves precision and recall.