Techniques for Similarity Searching in Multimedia Databases

Important task when trying to find patterns in applications involving mining different types of data such as images, video, time series, text documents, DNA sequences, etc. Similarity searching module is a central component of content-based retrieval in multimedia databases Problem: finding objects in a data set S that are similar to a query object q based on some distance measure d which is usually a distance metric Sample queries: 1. point: objects having particular feature values 2. range: objects whose feature values fall within a given range or where the distance from some query object falls into a certain range 3. nearest neighbor: objects whose features have values similar to those of a given query object or set of query objects 4. closest pairs: pairs of objects from the same set or different sets which are sufficiently similar to each other (variant of spatial join) Responses invariably use some variant of nearest neighbor finding