A
tutorial on interactive browsing of image collections
Gerald Schaefer, Loughborough
University
Image collections, both private and commercial, are growing rapidly
and hence efficient and effective tools for managing these databases
are highly sought after. Content-based approaches, based on the
principle of visual similarity derived from image features, seem
necessary as most images are unannotated. However, typical
content-based retrieval systems have shown only limited usefulness.
In this tutorial, we will look at a variety of techniques and
methods for effective and intuitive image database visualisation and
browsing as an alternative to retrieval-based approaches. We will
look at how image databases are visualised in the three main
approaches of mapping-based, clustering-based and graph-based image
database navigation systems, how intuitive browsing operations are
supported, how image databases can be browsed employing non-desktop
systems (such as VR hardward, or mobile devices), and how the
effectiveness of image browsing systems can be evaluated.