Signature quadratic form distances for content-based similarity

Abstract

Determining similarity is a fundamental task in querying multimedia databases in a content-based way. For this challenging task, there exist numerous similarity models which measure the similarity among objects by using their contents. In order to cope with voluminous multimedia data, similarity models are supposed to be both effective and efficient. To this end, we introduce the Signature Quadratic Form Distance measure which allows efficient similarity computations based on flexible feature representations. Our new approach bridges the gap between the well-known concept of Quadratic Form Distances and feature signatures. Experimentation indicates that our similarity measure is able to compete with state-of-the-art similarity models regarding effectiveness of content-based similarity search. Moreover, our Signature Quadratic Form Distance outperforms the established Earth Mover's Distance in efficiency: we obtain a speed-up factor of greater than 50.