Article View: csd.grad
Article #3578LAMP Seminar 10/13/98 (fwd)
From: David S. Doermann
Date: Tue, 13 Oct 1998 00:00
Date: Tue, 13 Oct 1998 00:00
36 lines
1855 bytes
1855 bytes
LAMP Seminar
Language and Media Processing Laboratory
Conference Room 4406
A.V. Williams Building
University of Maryland
------------------------------------------------------
Tues, October 13, 1998 1 pm
John D. Hobby
(Joint work with Tin Kam Ho)
LUCENT TECHNOLOGIES
ABSTRACT
Proper display and accurate recognition of document
images are often hampered by degradations caused by
poor scanning or transmission conditions. We propose
a method to enhance such degraded document for better
display quality and recognition accuracy. The essence
of the method is in finding and averaging bitmaps of
the same symbol that are scattered across a text page.
Outline descriptions of the symbols are then obtained
that can be rendered at arbitrary resolution.
This talk will explain the algorithm and show how it
performs on fax images and how it can improve OCR
recognition accuracy.
------------------------------------------------------
Please send email to denise@cfar.umd.edu for additional
information.
Seminar Series Schedule: http://documents.cfar.umd.edu/LAMP
Technical Details
Message-ID:
<Pine.SOL.3.95.981013080628.28911D-100000@alnitak.cfar.umd.edu>Path:
arc1-ca.pugleaf.net!unknown!not-for-mailShow Full Headers
Complete Article Headers
X-Google-Language: ENGLISH,ASCII-7-bit X-Google-Thread: 10f4d5,6e1f9cd8ee2da772,start X-Google-Attributes: gid10f4d5,public From: doermann@cfar.umd.edu (David S. Doermann) Subject: LAMP Seminar 10/13/98 (fwd) Date: 1998/10/13 Message-ID: <Pine.SOL.3.95.981013080628.28911D-100000@alnitak.cfar.umd.edu> X-Deja-AN: 400597047 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Complaints-To: abuse@cs.umd.edu X-Trace: cronkite.cs.umd.edu 908280672 15687 128.8.128.180 (13 Oct 1998 12:11:12 GMT) Organization: U of Maryland, Dept. of Computer Science, College Park, MD 20742 Mime-Version: 1.0 NNTP-Posting-Date: 13 Oct 1998 12:11:12 GMT Newsgroups: csd.grad