A Bayesian Framework for Content-Based Indexing and Retrieval

We pose the content-based retrieval problem as a problem of statistical inference and develop a Bayesian framework for indexing and retrieval in the context of large multimedia databases. All the indexing is carried out in the compressed domain and leads to eecient retrieval without compromise of the compression eeciency. The framework allows the integration of information from diierent sources and modalities as a way to eliminate some of the most signiicant limitations of the query by example search paradigm, and all the model parameters can be learned from training examples.