ERCIM Workshop Proceedings - No. 97-W004

Proceedings in pdf

To order a paper copy of the report, fill in the form at the ERCIM workshop reports page


Image Indexing and Retrieval

San Miniato, 28-30 August 1997

ISBN 2-912335-03-5


 Title  Author(s)  Formats *
Introduction Pasquale Savino and Carlo Meghini, CNR       html
Invited talk:
Visual Querying by Color Perceptive Regions
A. Del Bimbo, P. Pala, Dipartimento di Sistemi e Informatica, Università di Firenze pdf .rtf  
Image retrieval using local characterization Cordelia Schmid, Roger Mohr, INRIA ps.gz pdf    
Invited talk:
Image and Video Modeling and Understanding
Fang Liu, MIT Media Lab ps.gz pdf    
Research on Human-centered Design and Evaluation of Multimode Image Retrieval C. Olivia Frost, School of Information; Roberta Johnson, Space Physics Research laboratory; Sang Wook Lee, Electrical Engineering and Computer Science; Yi Lu Murphy, Electrical and Computer Engineering, UM-Dearborn   pdf rtf  
Invited talk:
Finding images in large collections
David Forsyth, Jitendra Malik, Margaret Fleck, Serge Belongie and Chad Carson, University of California at Berkeley pdf .rtf  
The terminological image retrieval model C. Meghini, F. Sebastiani, U. Straccia, CNR-IEI Pisa ps.gz pdf    
Browsing through and searching for similar images in astronomical archives using data-density based image icons Andre Csillaghy, Institute for Astronomy, ETH-Zentrum, Zurich ps.gz pdf    
Mixing classes and prototypes: An object oriented approach to semantic image indexing Youssef Lahlou, GMD ps.gz pdf    
Invited talk:
Semantics from Interactions in Image Databases
Simone Santini, University of California, San Diego   pdf rtf  
Image Processing Techniques for video content extraction Ines Oliveira, Nuno Correia, Nuno Guimaraes, INESC/IST, Lisboa ps.gz pdf  
Invited talk:
Multi-stage Classification of Images from Features and Related Text
J.R. Smith (IBM T.J. Watson Research Center), Shih-Fu Chang (Dept. of Electrical Eng., Columbia University) ps.gz pdf    
The theory and practice of similarity searches in high dimensional data spaces Roger Weber (ETH), Pavel Zezula (IEI-CNR) ps.gz pdf    





Images have always been a fundamental communication medium. The impressive achievements in information technology of the last decade have brought images to play a central role in computerized information systems, thus opening an enormous application area. The amount of images stored and accessed in electronic form is already very large, and is rapidly increasing. It is expected that images will be a major content resource of digital libraries.

In this context, the ability to select from a large collection those images that are relevant to a user request, specified either in visual or in textual terms, is at the heart of the image retrieval problem, and, at the same time, a fundamental functionality of a modern information retrieval system. Queries expressed in visual terms (e.g., images themselves or elements thereof) are handled on the basis of similarity criteria, and thus aim at providing the user with images that "look like" the query; this is "content-based image retrieval", a form of retrieval currently being studied by the research community. On the other hand, queries expressed in textual terms, such as natural language sentences or formal expressions using a controlled vocabulary with a possibly complex syntax, address the content of the images; this is known as "semantic content-based image retrieval".

The fourth workshop of the DELOS working group addressed the topic of "Image Retrieval" and was hosted by CNR in San Miniato, a small medieval town not far from Pisa, from 28-30 August, 1997. DELOS is a Working Group funded by the IT Long Term Research programme of the European Commission to study and investigate existing and emerging technologies and issues relevant to digital libraries.

The Workshop brought together 20 participants from eight different European countries, as well as 6 invited speakers, one from Europe and 5 from the United States. The workshop thus provided a significantly broad picture of the research on image retrieval under way both in Europe and in the US.

The invited speakers' presentations addressed different aspects of the image retrieval problem. In particular, Alberto Del Bimbo, from the University of Florence, gave a comprehensive overview of content-based image retrieval. Fang Liu from the MIT Media Lab illustrated a number of digital library projects completed or in progress in the Vision and Modeling Group at the MIT Media Laboratory. David Forsyth from the University of California at Berkeley presented the results of a research project aiming at the retrieval of pictures on the basis of the objects depicted. Simone Santini from the University of California at San Diego investigated the problem of meaning in image databases, arguing that the meaning of an image should be considered as a result of the interaction between the user and the database, rather than as an intrinsic property of the images. John Smith from the Image and Advanced Television Laboratory of Columbia University presented a new approach for automatically classifying images using both image features and related text. He argued that the synergy of textual and visual information in Web documents provides a great opportunity for improving the image indexing and searching capabilities of Web image search engines. Olivia Frost from the University of Michigan presented a project under way at her university aimed at exploring the development and evaluation of multimode retrieval schemes which employ both image and text and which are multiple path, iterative and user-directed.

Other presentations from the European researchers ranged from modeling, to the study of efficient access methods supporting similarity retrieval, feature extraction methods and applications. In particular, Carlo Meghini (IEI-CNR Pisa) presented an approach for combining syntax and semantics in image retrieval, while Youssef Lahlou (GMD) described an object-oriented model for semantic image indexing. The presentation of Roger Weber (ETHZ Zurich) and Pavel Zezula (IEI-CNR Pisa) illustrated the problems related to the definition of access structures for similarity retrieval in high dimensional data spaces. Specific solutions were proposed. Roger Mohr (INRIA) presented an approach to image retrieval that uses local characteristics; Ines Oliveira (INESC Lisbon) illustrated a comprehensive set of image processing techniques for video content extraction. Finally, Andre Csillaghy (ETHZ Zurich) presented an application of image browsing and retrieval, applied to astronomical archives.

These proceedings include extended abstracts of the talks given at the Workshop.

We should like to that ESPRIT and ERCIM for supporting the Workshop, and our collegue Tarina Ayazi, as well as the local people at San Miniato, to make it happen.

Carlo Meghini

Pasquale Savino

The DELOS Working Group is a part of the ESPRIT Long Term Research Programme (LTR No. 21057) and is managed by ERCIM (European Consortium for Informatics and Mathematics)

The DELOS Partners are

ERCIM members:

Non-ERCIM members:

For additional information, please contact Costantino Thanos at:

Istituto di Elaborazione della Informazione
Consiglio Nazionale delle Ricerche
Via Santa Maria 46
I-56126 Pisa
Tel: +39 50 593492
Fax: +39 50 554342