Content-based image retrieval: Advanced topics

Abstract

Image collections are growing at a rapid rate, motivating the need for efficient and effective tools to search through these databases. Content-based image retrieval (CBIR) techniques extract features directly from image data and use these to query image collections. In this paper, we focus on some more advanced issues in CBIR, namely the extraction of image features from compressed images, the use of colour invariants for image retrieval, and image browsing systems as an alternative to direct retrieval approaches. © 2011 Springer-Verlag Berlin Heidelberg.