(DBWORLD) Workshop on Content-Based Image Retrieval - call for papers

Joemon M Jose (jj@scms.rgu.ac.uk)
Thu, 18 Sep 1997 19:46:55 +0100

CALL FOR PAPERS

THE CHALLENGE OF IMAGE RETRIEVAL

A Workshop on Content-Based Image & Video Retrieval
February 5, 1998, University of Northumbria at Newcastle, UK

This one-day Research Workshop forms the first day of a two-day
conference on image retrieval to be held in Newcastle upon Tyne on 5-6
February 1998. It aims to provide a forum for presenting new research
ideas and results in the rapidly-growing field of content-based image
retrieval. It will be of prime interest to researchers in image retrieval,
and practitioners wishing to keep up to date with the latest research in
the field. The Workshop will be followed by a one-day Symposium on the
wider aspects of image retrieval on February 6. Delegates may register
for either or both days of the conference. For further details see
http://www.scms.rgu.ac.uk/research/ir/cfp.html.

CALL FOR PAPERS

Original research papers are solicited for the research workshop
describing work in progress or completed work on any topic related to
image and video storage and retrieval. Possible topics include, but are
not limited to:

Feature extraction and representation
Image search and browsing techniques
Query models, paradigms and languages for image retrieval
Similarity retrieval of images and video
Semantic retrieval of images and video
Evaluation and user issues
Neural network techniques for image retrieval
Image retrieval applications and systems
User interface issues
Database architectures for image retrieval
Image crawling and the net

BACKGROUND

Collections of digital imagery are widely used in various aspects of
life. Examples include, stock photo libraries, movie libraries,
satellite imageries etc. Research in information retrieval, database
management, computer vision and image processing is converging towards
providing content-based access to such image and video libraries.

The fundamental issues in the design of multimedia databases
revolve around effective and efficient selection of multimedia
documents which satisfy a visual query. The major issues facing
content-based retrieval are: data organization, selecting appropriate
features for content representation, query specification and
matching. To provide effective retrieval, we need to find which
features are significant in a particular domain and how these features
can be used to search for images of interest. In the context of image
and video databases, this means research is needed to extract both
generic and query-specific representations of image and video data
exposing features such as color, texture, motion, other geometric and
text attributes. Moreover, effective ways of organizing image and
video data representations is needed to enable fast search of the
databases.

Integration of multiple search modalities, both at the level of
algorithms, and user interface will be increasingly essential in
information systems. A research emphasis is needed on incorporating
multiple models, especially the ones for shape, color, texture,
geometry, text and syntax. Research is also needed to exploit the
presence of the user, such as obtaining incremental specifications for
a query and using user feedback to combine semantic, perceptual, and
other criteria in evaluating the results of a query. Finally, new
database design frameworks are needed that combine visual information
with more traditional database information to respond to queries.

To evaluate the effectiveness of image retrieval systems, we need
to develop realistic evaluation strategies, including test databases
of realistic size in domains of interest along with some real tasks
from the same domain, and measures of similarity that allow variations
in perceptual, semantic, and other criteria and including measures of
accuracy and efficiency in assisting the user. In addition, users must
be brought to the centre stage of the evaluation.

SUBMISSION DETAILS

Authors are asked to submit a 1500 word extended summary, in English,
which clearly indicates the originality of their work and its
contribution to the field of image retrieval. Summaries should be
submitted to the Conference Chair, either electronically or on paper,
to arrive no later than MONDAY 24 NOVEMBER 1997. Authors whose
contributions are accepted for presentation will be asked to submit a
complete version of their paper (no more than 5000 words) no later
than the date of the workshop. All attendees at the workshop will
receive a copy of the published proceedings. Authors submitting
on paper are asked to send 3 copies to Prof David Harper, Conference
Chair, The Challenge of Image Retrieval, School of Computer and
Mathematical Sciences, Robert Gordon University, Aberdeen AB25 1HG,
together with a covering letter containing contact information.
Authors will be notified of acceptance or rejection no later than
5 January 1998.

Guidelines for electronic submimission can be found at
http://www.scms.rgu.ac.uk/research/ir/sub.html

ORGANIZING COMMITTEE:

Mark Dunlop, University of Glasgow
John Eakins, University of Northumbria at Newcastle
Peter Enser, University of Brighton
Margaret Graham, University of Northumbria at Newcastle
David Harper (Chair), Robert Gordon University, Aberdeen
Joemon Jose, Robert Gordon University, Aberdeen
Martin Nail, British Library Research and Innovation Centre

SPONSORS:

British Computer Society - Information Retrieval Specialist Group
British Library Research and Innovation Centre
Institute for Image Data Research, University of Northumbria at
Newcastle
School of Computer & Mathematical Sciences, The Robert Gordon
University, Aberdeen

IMPORTANT DATES:

Deadline for Submission: 24 November 1997
Notification of Acceptance: 5 January 1998
Camera-ready Papers due: 5 February 1998

--------------------------------------------------------------------------
The dbworld list reaches many people, and should only be used for
messages of general interest to the database community.
To subscribe or unsubscribe yourself (or optionally (address)) from
dbworld, send a msg to majordomo@cs.wisc.edu with one of these lines:
subscribe dbworld (address)
unsubscribe dbworld (address)
To find out more options send a msg with the line:
help
--------------------------------------------------------------------------