|
 |
Daniel P. Lopresti
Professor and Chair
Computer Science
&
Engineering
Lehigh University
19 Memorial Drive West
Bethlehem, PA 18015-3084 USA |
Phone:
|
(610) 758-5782 |
Fax:
|
(610) 758-4096 |
Email*:
|
 |
|
|
Office:
|
Packard Lab 350 |
Hours:
|
by appointment |
|
|
 |
Daniel Lopresti
received his bachelor's
degree from Dartmouth in 1982 and his Ph.D. in computer science from
Princeton in 1987. After completing his doctorate, he joined the
Department of Computer Science at Brown and taught courses ranging from
VLSI design to computational aspects of molecular biology and conducted
research in parallel computing and VLSI CAD. He
went
on to help found the Matsushita Information Technology Laboratory in
Princeton,
and later also served on the research staff at Bell Labs where his work
turned to document analysis, handwriting recognition, and biometric
security.
In 2003, Dr.
Lopresti joined the
Department of Computer Science and Engineering at Lehigh where he leads
a research group examining fundamental algorithmic
and systems-related questions in pattern recognition, bioinformatics,
and security. Dr. Lopresti is co-director of the Lehigh Pattern Recognition
Research (PatRec) Lab. On July 1, 2009, he became Chair of the
Department of Computer Science and Engineering.
| Recent
News of Note |
|
|
|
New Paradigm for Pattern Recognition Research
We are
investigating a fundamentally new approach to conducting experimental
pattern recognition research. Based on advances made possible by Web
2.0 technologies, our vision addresses a number of serious issues with
the status quo, including overreliance on small standard datasets,
implicit bias in testing, and irreproducibility of experimental
results. For more details on this idea which we call "DARE," click here. |
|
Document Analysis and Exploitation
We have had an
active research effort in the area of document analysis and
exploitation for several years now. Much of this work has been
conducted in collaboration with colleagues at BBN Technologies with
funding from DARPA, the Defense Advanced Research Projects Agency.
Henry Baird and I are principal investigators, but recent congressional
funding we received has expanded the project to include other
colleagues, including Hank Korth. To read a news article about the new
award, click here.
|
Electronic Voting
I serve as an independent expert in
the Banfield v. Cortés lawsuit challenging the use of certain
electronic voting machines in the Commonwealth of Pennsylvania. Click here to learn
more about the case, which has been in progress for several years now.
A recent ruling
by the judge in the case has set the stage for independent examination
of Pennsylvania's e-voting systems. The details are now being worked
out by parties from both sides.
The PERFECT Project
We recently wrapped up a modest NSF CyberTrust grant to study
issues surrounding the reliable processing of voting records, including
paper ballots. Investigators on the project included George Nagy
from RPI, Elisa Barney Smith from Boise State, Chris Borick from
Muhlenberg, and Ziad Munson and myself from Lehigh. PERFECT is an
acronym that stands for "Paper and Electronic Records For Elections:
Cultivating Trust." Click here
for the PERFECT project website.
For access to an important new collection of scanned ballot images from
a real election, click here.
We have acquired examples of two full-face electronic voting systems
manufactured by
Danaher and Sequoia. These systems match those used in several PA
counties, and were purchased from government surplus auctions on the
web. For more information and media coverage, click below:
For other past
news
on the e-voting issue, click here.
|
|
Bioinformatics
Stefan Maas from Biological Sciences and I having been working for
several years to develop
techniques for searching large genetic databases for evidence of RNA
editing events. Click here
for a recent news article about the project. A number of students have
participated in this research, including two teams that were part of
Lehigh's Biosystems
Dynamics
Summer Institute, funded by the Howard Hughes Medical
Institute (HHMI).
|
* My
email address is expressed in image format to make it more difficult
for "bots" to harvest it for spam purposes.
|
|
|
