Interaction models and relevance feedback in image retrieval

Heesch, Daniel and Rüger, Stefan (2007). Interaction models and relevance feedback in image retrieval. In: Zhang, Yu-Jin ed. Semantic-Based Visual Information Retrieval. IRM Press, pp. 160–186.

URL: http://www.igi-global.com/bookstore/Chapter.aspx?T...

Abstract

Human-computer interaction is increasingly recognised to be an indispensable component of image retrieval systems. A typical form of interaction is that of relevance feedback whereby users supply relevance information on the retrieved images. This information can subsequently be used to optimise retrieval parameters. The first part of the chapter provides a comprehensive review of existing relevance feedback techniques and also discusses a number of limitations that can be addressed more successfully in a browsing framework. Browsing models form the focus of the second part of this chapter where we will evaluate the merit of hierarchical structures and networks for interactive image search. This exposition aims to provide enough detail to enable the practitioner to implement many of the techniques and to find numerous pointers to the relevant literature otherwise.

Viewing alternatives

Item Actions

Export

You can export this page using these formats

About

• Item ORO ID
• 22054
• Item Type
• Book Section
• ISBN
• 1-59904-372-6, 978-1-59904-372-2
• Keywords
• information retrieval; content-based image retrieval; query by example; human-computer interaction; relevance feedback; browsing; image networks; image polysemy
• Academic Unit or School
• Faculty of Science, Technology, Engineering and Mathematics (STEM) > Knowledge Media Institute (KMi)
  Faculty of Science, Technology, Engineering and Mathematics (STEM)
• Depositing User
• Stefan Rüger