HOME | PROGRAMME | LECTURERS | PARTICIPANTS | LOGISTICS

Image Retrieval

Henning Mueller(1) and Thomas Deselaers(2)
(1) University Hospitals of Geneva, Switzerland
(2) Computer Vision Laboratory, Swiss Federal Institute of Technology - ETH Zurich, Switzerland

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 show approaches to fusing the efforts from content-based image retrieval with the available text-based image searching solutions, including multilingual 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 will focus 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
• Image retrieval in a multilingual context

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
3. Text-based image retrieval
   • methods for feature weightings
   • stemming and other pre-treatment
   • strategies for multilingual information retrieval
4. Combination
   • feature-based
   • direct
   • direct fusion in the continuous approach
   • direct fusion in the discrete approach
5. Fusion by refining
6. Relevance feedback
   • instance-based relevance feedback
   • model-based relevance feedback
   • probabilistic relevance feedback
7. Evaluation of image retrieval
   • evaluation campaigns
   • evaluation of interactive performance
8. Cross-language image retrieval and ImageCLEF
9. Summary

Recommended reading

One technical article that can help participants understand the principle techniques is:
AWM Smeulders, M Worring, S Santini, A Gupta, R Jain, Content-Based Image Retrieval at the End of the Early Years, IEEE Trans on Pattern Anal Mach Intell 22, (2000), 1349-1380.

Course Material

1. Introduction
2. Efficient Algorithms for Image Retrieval
3. Content Bsed Image Retrieval
4. Text-based Iì(Image) Retrieval
5. Combining Textual- and Content-based Image Retrieval
6. Relevance Feedback
7. Evaluation and Image Retrieval
8. Summary and Conclusions