Tutorial Image Retrieval @ ICPR 2008

Henning Müller and Thomas Deselaers gave a tutorial on image retrieval at ICPR in December 2008.

Abstract

Image retrieval has been receiving increasing interest due to the vast amount of images publicly available on the Internet. Most image sharing sites, such as FlickR, allow for text/tag-based image searching. In the research community, content-based image retrieval has been under investigation since the early 1990s. The tutorial will give show approaches to fusing the efforts from content-based image retrieval with the available text-based image searching solutions, including multi-lingual approaches. Therefore, a short introduction into content-based image retrieval and text-retrieval will be given. Different approaches to fusing these will be discussed and further topics such as user-interaction, retrieval system architecture, and benchmarking issues will be
presented.

The tutorial focuses on image retrieval from different perspectives:

• content-based image retrieval, i.e. finding images by their visual content
• text-based image retrieval, i.e. finding images using textual information
• combination of the above

Outline

1. introduction/motivation (applications)/problems
2. content-based image retrieval:

• methods (continuous approach/discrete approach)
• image processing basics (very short)
• features for image retrieval
• relationship between the various approaches

• methods for feature weightings
• stemming and other pre-treatment
• strategies for multilingual information retrieval

• feature-based
• direct
• direct fusion in the continuous approach
• direct fusion in the discrete approach

• instance-based relevance feedback
• model-based relevance feedback
• probabilistic relevance feedback

• evaluation campaigns
• evaluation of interactive performance