Skip to content

Toggle service links


The overall aim of the project was to create a web-based image and video browser for content-based retrieval that integrates the current research into browsing and searching into a unified interface. uBase Demo

The resulting browser provides the user with the power to browse a large image collection quickly and accurately. The project builds upon the work of Daniel Heesch into searching and browsing strategies.

The project's main focus was on the important issues of integrating the searching and browsing mechanisms, and improving the user-interface. The browser seamlessly integrates the following main features:

  • Search with relevance feedback, browsing results by rank
  • Hierarchical browsing
  • Lateral browsing using NNk network
  • Temporal browsing
  • Historical browsing
  • Image/video viewer

The browser and search engine is implemented under a client-server model. This enables us to centralise the search engine backend and the interface to the image collection. By using a Java applet-servlet model, we can provide a platform-independent client that can be loaded from a webpage.


Alexander May Paul Browne Stefan Rueger


InactiveVisit Website