|
TC3 - IAPR Planned
Activities 9/2002 –
8/2004 |
1. Scope
The
scope of the Technical Committee 3 is mainly related to the use of artificial neural networks (ANN) in the
field of pattern recognition (PR). Two of the main objectives are the reduction
of the gap between the PR and ANNs communities, as well as an attempt to
identify potentialities of ANNs in the PR domain. In the last few years several
models (including algorithms for processing graphs and trees) have been
proposed which are likely to be very useful for pattern recognition. The
current scope of TC3 includes not only neural networks, but also what is
presently called Computational
Intelligence, including fuzzy systems, evolutionary computing like genetic
algorithms, and those branches of statistics that are relevant to the above
fields. A very important objective of
the committee is also to provide a careful evaluation of the results of the
research by encouraging people to compete on appropriate contests.
In
the last two years TC3 has provided a technical cooperation with the following
conferences and special sessions, which are related to its activities:
·
Neural Networks for Instrumentation, Measurement, and
Related Industrial Applications, NATO-ASI
9-20 October 2001, Crema , Italy.
·
VI Ibero-American Symposium on Pattern Recognition
SIARP'2001. October 12 - 14, 2001, Florianopolis – Brazil
·
Limitations and Future Trends in Neural Computation,
Siena, 22-24 October 2001
·
Computational Intelligence in Financial Engineering -
World Congress on Computational Intelligence, May 12-17, 2002. Honolulu -
Hawaii.
2.
Plans for next two years
2.1
Organization
of the first TC3 workshop.
We are planning to have this
workshop next year, tentatively in conjunction with ICDAR2003. The workshop
will be organized in Florence (see enclosed preliminary call for papers). The
official call for papers will be announced by September 30, 2002.
2.2 Organization
of contests.
We are planning to include a
contest within the First Workshop of TC3 on graphical item recognition using
neural networks and related approaches. The idea of organizing a contest,
however, is not restricted to the scope of the workshop, but is to propose
contests aimed at comparing in a systematic way novel approaches which appear
in the literature. In particular this will create the typical pattern of a TC3
Workshop: In addition to typical submission, one is asked to competed on data
which are given by the organizers of the workshop. In so doing we rely on the
principle that it is very hard to "bless" a given contest, but every
year new contests will be established so as not to bias the contest to specific
approaches. The contest created within the TC3 might be partially or totally
acquired by other IAPR technical committes. This activity is considered of
crucial importance since it might open fruitful interactions with other
technical committees on the actual role of neural networks models in pattern
recognition.
2.2 Electronic News Letter.
The
news letter will be published every four months (February 28, June 30, October
30).
The
first edition of will be published at
the end of October 2003.
2.3 Updating of
mailing lists.
Mailing-lists of researchers
in the fields of Neural Networks and Computational Intelligence in Financial
Engineering. have been prepared which come from an opportune filtering of the
lists of international conferences like IJCNN2000. New items will be added
taking into account lists of participants of recent conferences like ICPR 2002.
According to the decisions
made by IAPR, the integration of mailing lists with those maintained at the
main web site will be considered.
2.4 Updating of
the web site.
The Web site of the technical committee has been recently renewed (www.dii.unisi.it/TC3). The site describes the aim of TC3, the events for which there is a technical cooperation, and collects a number of useful references for standard dataset typically used especially in the community of neural networks.
The web site will be properly enriched and updated so as to include the news letters, the link to the TC3 Workshop, to information on the contests and, generally, all the information which are likely to be useful for the members of the community. In particular, pointers to public domain software for using ANNs will be added, as well as a large bibliographic reference on papers related to PR applications using ANNs.
2.5 Call for
membership.
In order to enlarge the audience of TC3, a “call for membership” will be posted to the mailing list addresses. In addition announcements will be made in appropriate places, including a presentation of TC3 and of its workshop in IAPR’s Newsletters.
3.
Chairing for next two years
Professor Marco Gori proposes the plan for the
next two years and recommends Dr. Simone Marinai (University of Florence) as a co-chair. He is expected to support
to the organization of the mentioned activities, with special emphasis on the TC3 workshop and the newsletter.
4.
Biosketches
Marco Gori received the Laurea in electronic engineering from Università di Firenze, Italy, in 1984,
and the Ph.D. degree in 1990 from Università
di Bologna, Italy. From October 1988 to June 1989 he was a visiting student
at the School of Computer Science (McGill University, Montreal).
In 1992, he became an Associate
Professor of Computer Science at Università
di Firenze and, in November 1995, he joint the Università di Siena, where he is currently full professor.
His main research interests are
in neural networks, pattern recognition, and applications of machine learning
to information retrieval on the Internet. He has leaded a number of research
projects on these themes with either national or international partners, and
has been involved in the organization of many scientific events, including the
IEEE-INNS International Joint Conference on
Neural Networks, for which he
acted as the program chair. (July 24-28, 2000),
Dr. Gori serves (served) an
Associate Editor of a number of technical journals related to his areas of
expertise, including Pattern Recognition, the IEEE Trans. Neural Networks,
Neurocomputing, Neural Computing Survey, Pattern Analysis and Application, the
International Journal on Computer Research, and the International Journal on
Pattern Recognition and Artificial Intelligence.
He is the Italian chairman of
the IEEE Neural Network Council (R.I.G.), is acting as the co-chair of the TC3
technical committee of the IAPR (International Association for Pattern
Recognition) on Neural Networks, and is the President of the Italian
Association for Artificial Intelligence.
Dr. Gori is a fellow of the
IEEE.
Contact informations:
Marco Gori
Dipartimento
di Ingegneria dell'Informazione
Università
di Siena
Via
Roma, 56 - 53100 Siena (Italy)
Email: marco@ing.unisi.it
Dr. Simone Marinai
Simone
Marinai received the Laurea in Electronic Engineering in 1992, from Università di Firenze, Italy. He
obtained the PhD degree in computer science in 1996 with a thesis on the
extraction of information from structured documents. In 1995 he has been a
visiting scientist at Cenparmi lab
(Concordia University - Montreal Canada). His main research interests are in
pattern recognition, neural networks, and document processing applications.
Currently he is Assistant Professor at Università
di Firenze, where he teaches, among the others, neural networks
applications in the field of document image analysis in the Artificial
Intelligence course. In 2001 he was co-author (with Marco Gori) of the tutorial
`` Artificial Neural Networks for
Document Analysis and Recognition'', that was organized in conjunction with
the ICADR 2001. The same tutorial has
been organized in conjunction with ICPR
2002. Simone Marinai was the chairman of the workshop `` Document Analysis and Understanding for Document Databases''
(DAUDD) held in 1999 in conjunction with the DEXA conference. He is member of several conference program
committees, and he is currently Associate Editor of the `` Electronic Letters on Computer Vision and Image Analysis''
journal.
Contact
informations:
Simone
Marinai
Dipartimento
di Sistemi e Informatica
Università
di Firenze
Via
S. Marta, 3 - 50139 Firenze (Italy)
Email: simone@dsi.unifi.it