In addition to presentations of invited and solicited
papers, the workshop will have two plenary talks delivered by renowned experts
in their fields.
A
Million Images a Day
Stephen L.
Schultz
Chief Technology Officer for Pictometry International
Corporation
Abstract:
Pictometry's oblique metric image capture and processing
system can produce over one-million images a day and has captured 70% of the
populated United States
in the past two years. Many unique
technical challenges had to be overcome to achieve these numbers and still more
lie ahead. This talk will discuss some
of the major hurdles solved, both hardware and
software, and some that are still being solved.
Specific topics discussed will include camera and lens design, demosaic algorithms, and specular
reflection color balancing issues.
Speaker Biography:
Stephen
L. Schultz, Chief Technology Officer for Pictometry
International Corp., has been working in the remote sensing industry since he
first joined the Digital Imaging and Remote Sensing (DIRS) Labs at the
Rochester Institute of Technology (RIT) in 1985. First hired to write a device driver for a
Gould/DeAnza Image Array Processor, Mr. Schultz
quickly completed that task and then began the creation of a general purpose
image processing library for both VMS and Unix based
computers, as well as utilizing image array processors, if available.
In the late 80's, as the DIRS labs
grew into the Chester F. Carlson Center for Imaging Science, his focus shifted
to infrared image analysis and frequency domain processing. His implementation of the Fast Fourier
Transform was 43% faster than the implementation delivered with the IMSL
numerical software libraries. He also
worked heavily in developing algorithms to correct for aircraft movement in
airborne scanner systems as well as full-frame capture devices.
In the early 90's his focus shifted
again, this time to synthetic image generation, especially in the far and thermal
infrared spectrums. He completed a
complex model of infrared irradiance that incorporated industry models for
solar irradiance, sun angles, atmospheric and aerosol absorption, infrared
transmission, thermal conductance, and angular emissivity.
In 1994, Mr. Schultz began working
part-time on the development of a new approach to oblique photogrammetry
for Pictometry, Inc.
He left the Center for Imaging Science in 1996 to pursue this
opportunity full-time, becoming the company's Vice President of Engineering. By the end of the year, he had developed a
fully working system capable of capturing, processing, and analyzing oblique
metric images.
In 2001, Mr. Schultz was named
Senior Vice President and Chief Technology Officer for the newly formed Pictometry International Corp. In addition to providing the overall
technical direction for the company, Mr. Schultz has been responsible for the
creation of the company's intellectual property with two patents issued and seventeen
other patents in process.
In 2007, Mr. Schultz was named the
Distinguished Alumnus for the B. Thomas Golisano
College of Computing and Information Sciences at RIT.
Recent Advances in
Image and Video Recovery
Professor Aggelos K. Katsaggelos
Northwestern University
Abstract:
There is a plethora of image and
video processing applications in which information is lost during the
acquisition, processing, or transmission stages. These applications include
astronomical imaging (e.g., using ground-based imaging systems or extraterrestrial
observations of the earth and the planets), commercial and entertainment
photography, medical imaging, and molecular and cellular bioimaging.
A recovery problem is then required to be solved, according to which an
estimate of the original scene is obtained based on the observed data and prior
knowledge about the original image and the degradation process. Examples of
such problems are the restoration or deconvolution
problem, the super-resolution problem, the problem of removing compression and
transmission artifacts (concealment problem) and the inpainting
problem. In this talk we provide a review of the techniques presented in the
literature for solving a number of recovery problems. We then describe in
detail some of the recent advances and outstanding challenges in image
restoration, blind image restoration, and super-resolution, utilizing a
Bayesian framework. Experimental results are presented to illustrate and
compare the effectiveness of various approaches.
Speaker Biography:
Aggelos K. Katsaggelos received
the Diploma degree in electrical and mechanical engineering from the
Aristotelian University of Thessaloniki, Greece, in 1979 and the M.S. and Ph.D.
degrees both in electrical engineering from the Georgia Institute of
Technology, in 1981 and 1985, respectively. In 1985, he joined the Department
of Electrical and Computer Engineering at Northwestern University,
where he is currently professor. He was the holder of the Ameritech Chair of
Information Technology (1997-2003). He is also the Director of the Motorola Center
for Seamless Communications and a member of the Academic Affiliate Staff,
Department of Medicine, at Evanston
Hospital.
Prof. Katsaggelos has extensive
professional involvement. He is
currently a member of the Publication Board of the IEEE Proceedings, the IEEE
Technical Committees on Visual Signal Processing and Communications, the
Editorial Board of Academic Press, Marcel Dekker: Signal Processing Series,
Applied Signal Processing, Computer Journal, EURASIP
Journal on Image and Video Processing, and Advances in Multimedia. He has served as editor-in-chief of the IEEE Signal Processing Magazine
(1997-2002), a member of the Publications Board of the IEEE Signal Processing
Society, the IEEE TAB Magazine Committee, an associate editor for the IEEE Transactions on Signal Processing
(1990-1992), an area editor for the journal Graphical
Models and Image Processing (1992-1995), a member of the steering
committees of the IEEE Transactions on
Image Processing (1992-1997) and the
IEEE Transactions on Medical Imaging (1990-1999), a member of the IEEE
Technical Committees on Image and Multi-Dimensional Signal Processing
(1992-1998) and Multimedia Signal Processing, and a member of the Board of
Governors of the IEEE Signal Processing Society (1999-2001).
Prof. Katsaggelos has published
extensively and he is the editor of Digital Image Restoration (Springer-Verlag 1991), co-author of Rate-Distortion Based Video Compression (Kluwer
1997), co-editor of Recovery Techniques
for Image and Video Compression and Transmission, (Kluwer
1998), and co-author of Super-resolution
for Images and Video (Claypool, 2007) and Joint Source-Channel Video Transmission (Claypool, 2007). He is the co-inventor of fourteen
international patents, a Fellow of the IEEE (1998), and the recipient of the
IEEE Third Millennium Medal (2000), the IEEE Signal Processing Society
Meritorious Service Award (2001), and a co-recipient of an IEEE Signal
Processing Society Best Paper Award (2001), an IEEE International Conference on
Multimedia and Expo Paper Award (2006), and an IEEE International Conference on
Image Processing Paper Award (2007). He
is a Distinguished Lecturer of the IEEE Signal Processing Society for 2007-08.
Workshop Registration
Fees are kept to a minimum and are primarily intended to cover the costs of
coffee breaks, lunch, and book of paper summaries.
IEEE Members: $20 Non-IEEE Members:
$45
Students: $10 IEEE student member
$25 otherwise
Advanced registration is strongly encouraged by a substantial discount in
the registration fees because we need a headcount for ordering the food. Hence,
there will be a flat late fee of $10 for on-site registration. For advance
registration, simply send an email to dcoumou@d3engineering.com
by September 25th. Please indicate any dietary restrictions and whether you are
a student and an IEEE member.
All payments are due on-site by either check (payable to IEEE Rochester
Section) or cash.
In order to encourage
participation by students, we will present a best student paper award.
Workshop website: http://ewh.ieee.org/r1/rochester/sp/IP_workshop2007/workshop07.htm
Organizing Committee:
Majid Rabbani, Eastman Kodak Company
David Coumou, MKS Instruments,
Inc.
John Handley, Xerox Corporation
Gaurav Sharma, University
of Rochester
Eli Saber, Rochester Institute of
Technology
Final
Program
|
8:00AM~8:30AM
|
Registration and Welcome
|
|
|
|
|
8:30AM~10:10AM
|
Image Understanding
|
|
|
Session
Chair: Eli Saber
Recognizing
Human Activities using Boundary Points of Silhouettes
Natasha
Kholgade and Andreas Savakis
RIT
Computer Engineering
Activity
Recognition Using Limb Component Extraction
Jamie
Boeheim and Andreas Savakis
RIT
Computer Engineering
Liver
Segmentation from Abdominal CT
images using GVF snake
Raja'
S Alomari, Suryaprakash
Kompalli, and Vipin
Chaudhury
The
Department of Computer Science and Engineering
State University
of New York at Buffalo
Perceptual
Cost Function for Motion Detection
Thomas
B. Kinsman, Roxanne Canosa
Department
of Computer Science
Rochester
Institute of Technology
Analyzing
the Role of Visual Structure in the Recognition of Natural Image Content with
Multi-Scale SSIM
David
M. Rouse and Sheila H. Hemami
School of Electrical and Computer Engineering
Cornell University
|
|
|
|
|
10:10AM~10:30AM
|
Coffee Break
|
|
|
|
|
10:30AM~11:30AM
|
Image Communication
|
|
|
Session Chair: John Handley
Complexity
Constrained Rate-Distortion Optimization of Sign Language Video using an
Objective Intelligibility Metric
Frank
Ciaramello and Sheila Hemami
School of Electrical and Computer Engineering, Cornell University
Near
Lossless Bitonal Image Compression System
Jeremy
Pyle and Andreas Savakis
Computer
Engineering, Rochester Institute of Technology
On
the Trade-Off between Lifetime and Distortion in Visual Sensor Networks
Chao Yu, Stanislava Soro, Gaurav Sharma,
and Wendi Heinzelman
Electrical
and Computer Engineering, University
of Rochester
|
|
11:30AM~12:30PM
|
Morning Plenary
|
|
|
A Million Images a
Day
Stephen L. Schultz, Pictometry
International Corporation
|
|
12:30PM~1:30PM
|
Lunch Break
|
|
|
|
|
1:30PM~2:30PM
|
Color Imaging
|
|
|
Session
Chair: David Coumou
Conditions
for Color Misregistration Insensitivity in
Clustered-Dot Halftones
Basak Oztan (Univ.. of Rochester), Gaurav Sharma (Univ. of Rochester),
and Robert P. Loce (Xerox Corp.)
Substrate
Fluorescence: Friend or Foe?
Raja
Bala (Xerox Corp.), Reiner Eschbach (Xerox Corp.), Iris Zhao (RIT)
The
HDR Photographic Survey
Mark
D. Fairchild
Munsell Color Science Laboratory,
Rochester Institute of Technology
|
|
|
|
|
2:30PM~3:30PM
|
Afternoon Plenary
|
|
|
Recent Advances in
Image and Video Recovery
Professor Aggelos K. Katsaggelos
Northwestern University
|
|
|
|
|
3:30PM~3:50PM
|
Coffee Break
|
|
|
|
|
3:50PM~4:50 PM
|
Security and
Forensic Imaging
|
|
|
Session Chair: Gaurav Sharma
Non-Writer
Specific Handwriting Generation for the CAPTCHA Application
Achint Oommen Thomas,
Amalia Rusu,
Smruthi Mukund,
and Venu Govindaraju
State University
of New York at Buffalo
Graphical
CAPTCHA Embedded in Cards
Roman
V. Yampolskiy
Facial
Aging using Image Warping
Greyce Nogueira
Schroeder (UNICAMP – Brazil),
Ricardo Nagel Rodrigues – (SUNY at Buffalo), and Léo Pini Magalhães –(UNICAMP – Brazil)
|
|
|
|
|
4:50PM~5:00PM
|
Best
Student Paper Awards Announcement
|
Location
The workshop will take place at the Rochester Institute of Technology,
Chester F. Carlson Center for Imaging Science Auditorium, Building 76, 79 Lomb Memorial Drive, Rochester, NY 14623 (Parking Lot F).
