iapr

Newsletter 07

Hello everybody,

Well, ICDAR'93 is over and I first will use the opportunity to thank
the organizers once again. The conference was interesting and well
organized and I think we all appreciated our stay in Tsukuba. So
congratulations to our Japanese friends for a successful conference.

Many things were discussed in Tsukuba: scientific matters,
organizational matters and friendly matters (conferences are also a
good place to get acquainted with the real people behind the names in
the bibliography lists;-). I am sure that these different matters will
come up again in the coming months, also in this mailing list.
By the way, many of you in this mailing list will receive this 7th
issue of TC10 news as the first you get, as one consequence of ICDAR
was that I extended my mailing list !!! So welcome to the club, as we
say here in France !

But I am not going to write a report here about ICDAR'93 (I haven't
enough time for that just now...). I will just mention some of the
information which was given there, for the benefit of those who
couldn't attend.

ICDAR'95 was announced (the call for papers was available in Tsukuba).
It will be in Montreal, August 14-16 1995. It is noteworthy to know
that IJCAI will be in Montreal the week after, so this is a good
opportunity to combine two interesting conferences. The call for
papers for ICDAR'95 will probably be available in electronic format; I
will put it in this mailing list as soon as I get it. Note that paper
submission deadline is December 1st, 1994, so we have time yet!

There was also a meeting to decide where ICDAR'97 should be. There
were several candidates for the organization, and after a vote among
all attendees of the meeting, the result was that ICDAR'97 will be
held in Ulm, Germany.

We also had a TC10 meeting to discuss the planned workshop on graphics
recognition. Here are the minutes of this meeting.

-----------------------------
TC10 meeting, October 21st, Tsukuba.

Present: L. Cordella, D. Dori, O. Hori, R. Kasturi, J. Kreich,
G. Monagan, B. Pasternak, K. Tombre, K. Tomiyama,
K. Yamamoto

Karl Tombre presents a draft of the call for papers for the TC10
workshop. This workshop is planned to be held just before ICDAR'95.
R. Kasturi is willing to host the workshop at Penn State University.

Remarks were made by several people that this workshop must not drain
away good papers from the main ICDAR conference. A discussion follows
on the best way to organize the workshop. A consensus is reached not
to call for plain papers but rather to define a number of panels on
specific topics. For each of these topics, there could be 1 or 2 main
paper presentations giving the state of the art and stating the open
questions for the topic, followed by a number of shorter presentations
where each participant is invited to contribute by proposing solutions
to some of the questions or presenting results of his/her work. Each
session would be concluded by a panel discussion.
Therefore, the topics should first be defined (and every proposal is
welcome); a call for contribution by short abstracts of remarks would
then follow. We plan also time for working groups to discuss in detail
specific problems.

Each session should last at least 2 hours. All in all, it is decided
that a 2-days workshop is enough and the dates of August 10-11 are
considered to be good. The workshop should be limited to about 75
persons.

The program committee will modify the call-for-papers draft to reflect
this consensus; then the call for papers will be sent out. Discussions
are being held with IAPR authorities for the workshop to be an
official IAPR event.
---------------------------
So you will see the call for papers soon in this mailing list, I
think.

Just before leaving for ICDAR, I got the following information by mail
from R.M. Haralick; this can also be of interest to many of you:
---------------------------
RMH> From This email address is being protected from spambots. You need JavaScript enabled to view it. Tue Oct 12 09:38:34 1993
RMH> Message-Id: <This email address is being protected from spambots. You need JavaScript enabled to view it. >
RMH> Content-Length: 1645
RMH> From: This email address is being protected from spambots. You need JavaScript enabled to view it.
RMH> To: This email address is being protected from spambots. You need JavaScript enabled to view it.
RMH> Subject: UW CDROM
RMH> Date: Tue, 12 Oct 93 01:36:41 PDT

RMH> Perhaps you can include this in your next email distribution.
RMH> UW English Document Image Database I

A Database of Document Images for OCR Research

2 CD-ROM set containing 1147 document page images from English
Scientific and Technical Journals having

- Binary images scanned from 1st and other generation photocopies

- Binary and grayscale images scanned directly from technical journals

- Synthetic noise-free images generated from LaTeX files

- Document images from UNLV ISRI database

- All document images zoned and tagged

- Software for OCR performance evaluation

- Software for simulation of photocopy degradation

- Text ground truth generated from two independent data-entry
operators followed by three independent verifications

Each document page has associated with it

- Text ground truth data for each text zone

- Bounding box information for each zone on the page

- Coarse level attributes for each document page

- Finer level attributes (such as font size, alignment etc.) for each
zone

- Qualitative information on the condition of each page

AT & T Bell Labs degraded character images database

Price $200 plus $10 shipping and handling.
Make your P.O. out to
Intelligent Systems Laboratory
Dept. of Electrical Engineering, FT-10
University of Washington
Seattle, WA 98195
Attention: Dr. Robert M. Haralick

Phone: (206) 685-4974
FAX: (206) 543-3842
e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Please make checks payable to Intelligent Systems Laboratory,
Univ. of Washington.

---------------------------
Then, there is the announcement of a new information server and
mailing list service for document understanding, the DIMUND
information server, which several of you have probably already seen:

---------------------------

Attached is an announcement which is being released in the next several
days about the new Document Information Server and Mailing List serving
document researchers. We hope to expand the contents of the server via
submissions from the community.

I would like to encourage you to submit any "information" which may be
interest to the document understanding community. This includes TR's,
Pre-prints of papers, Calls for Papers, Conference Announcements, Database
Information, Public Domain Source Code, Bibliographic Information, etc.

Please take subscribe to the mailing list and pass this announcement on
to your colleagues.

Thanks,

Dave

---------------------------------------------------------------------------



-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-

ANNOUNCING
The DIMUND Document Information Server

Gopher Server and Mailing List

-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-

This system is under development as a repository for Document Understanding
information and resources. The site is housed with the Document Processing
Group at the University of Maryland and available via internet at the node
dimund.umd.edu, port 70.

Please take a moment to subscribe to the mailing list and explore the core
resources on the server.

Some of the information available on this server includes:

- Research Announcements, Calls for Papers and Conference Programs
- Document-List Digest Archive
- On-line access to a document understanding bibliography including
feature extraction, OCR, on-line recognition, text/graphics
discrimination, signature verification and related document
problems.
- A contribution directory for Document Understanding Resources
- source code
- technical reports
- database information
- Archives of document understanding internet utilities


****** Submissions of all relevant information are strongly encouraged. ******


SYSTEM ACCESS
-------------
Access to this information is available via

Gopher:
An interactive information server available at dimund.umd.edu, port 70
To add DIMUND Gopher to and existing system, use the following link:

Name=DIMUND Document Information Server
Type=1
Port=70
Path=1/
Host=dimund.umd.edu

Telnet:
Access is available on a temporary basis via telnet to dimund.umd.edu.
Use "gopher" as a login.

Anonymous FTP:
Access to the selected files on the server by connecting to
dimund.umd.edu. Upload capabilities are also available.

EMail:
Email Access to selected files stored on the server is available
through the document server (This email address is being protected from spambots. You need JavaScript enabled to view it. ).
The DOCUMENTS mailing list is also processed by the server


Gopher access is the most complete and easiest to use. Please take time to
browse through the system. Although the core resources will be compiled by
the University of Maryland, the success of such a system depends on user
support, contributions and advertising.


For additional help getting started, send a mail message containing the
following body

HELP

to This email address is being protected from spambots. You need JavaScript enabled to view it.


CONTRIBUTIONS
-------------

Contributions can be sent to This email address is being protected from spambots. You need JavaScript enabled to view it. in the format specified
in the Gopher file

USING_THE_SYSTEM/SUBMISSION_INSTRUCTIONS

or uploaded via anonymous FTP.

The format can also be obtained via email by sending a mail request to
This email address is being protected from spambots. You need JavaScript enabled to view it. containing the single line

HELP SUBMISSIONS


MAILING LIST
------------

A Document Understanding Mailing List (DOCUMENTS) is also available as part
of the document server.

Send a mail message to This email address is being protected from spambots. You need JavaScript enabled to view it.
containing the following body

SUBSCRIBE DOCUMENTS <first name> <last name>

For additional help with the mailing list or online bibliography searchs,
send a mail message containing the following body

HELP MAIL-LIST
HELP BIBSEARCH

to This email address is being protected from spambots. You need JavaScript enabled to view it.


QUESTIONS and COMMENTS
----------------------

Direct all questions to This email address is being protected from spambots. You need JavaScript enabled to view it.


-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-

Moderated by: Dr. David Doermann

-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
| Document Processing Group
Phone: (301) 405-4526 | Center For Automation Research
Fax: (301) 314-9115 | University of Maryland
Email: This email address is being protected from spambots. You need JavaScript enabled to view it. | College Park, MD 20742
| USA
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-

---------------------------
So any of you having Internet access and some gopher software on your
site can add this entry to your direct gopher pointers (that's at
least what I did...)

Well, this mail has already become quite long. Thanks for reading to
the end. As they say, we will be back on the air as soon as there are
fresh news to broadcast ;-)

Your TC-10 chairman,

--
Karl Tombre - INRIA Lorraine / CRIN-CNRS --- Email: This email address is being protected from spambots. You need JavaScript enabled to view it.
Post: Batiment LORIA, BP 239, 54506 Vandoeuvre CEDEX, France --or--
615 rue du jardin botanique, BP 101, 54602 Villers CEDEX, France
Phone: +33 83.59.20.71 --- Fax: +33 83.41.30.79 --or-- +33 83.27.83.19