Copy Link
Add to Bookmark
Report
VISION-LIST Digest Volume 11 Issue 15
VISION-LIST Digest Mon Apr 20 12:21:29 PDT 92 Volume 11 : Issue 15
- Send submissions to Vision-List@ADS.COM
- Vision List Digest available via COMP.AI.VISION newsgroup
- If you don't have access to COMP.AI.VISION, request list
membership to Vision-List-Request@ADS.COM
- Access Vision List Archives via anonymous ftp to FTP.ADS.COM
Today's Topics:
NIST Special Database 2: Structured Forms Reference Set (SFRS)
NIST Special Database 4: 8-Bit Images of Fingerprint Image Groups (FIGS)
Stereo Camera Calibration
Image sequence needed
Looking for Relational Datasets
Parallel Partitional Clustering
info wanted on curve descriptions
LAS ALAMOS NATIONAL LAB : Enquiry
----------------------------------------------------------------------
Date: Fri, 17 Apr 92 08:34:49 EDT
From: Darrin Dimmick X4147 <dld@magi.ncsl.nist.gov>
Organization: National Institute of Standards and Technology
formerly National Bureau of Standards
Subject: NIST Special Database 2: : Structured Forms Reference Set (SFRS)
NATIONAL INSTITUTE OF STANDARDS AND TECHNOLOGY
Announces a New Database
+-----------------------------+
| "NIST Special Database 2" |
+-----------------------------+
Structured Forms Reference Set
(SFRS)
The NIST database of structured forms contains 5,590 full page images of
simulated tax forms completed using machine print. THERE IS NO REAL TAX DATA IN
THIS DATABASE. The structured forms used in this database are 12 different
forms from the 1988, IRS 1040 Package X. These include Forms 1040, 2106, 2441,
4562, and 6251 together with Schedules A, B, C, D, E, F and SE. Eight of these
forms contain two pages or form faces making a total of 20 form faces
represented in the database.
Each image is stored in bi-level black and white raster format. The images in
this database appear to be real forms prepared by individuals but the images
have been automatically derived and synthesized using a computer and contain no
"real" tax data. The entry field values on the forms have been automatically
generated by a computer in order to make the data available without the danger
of distributing privileged tax information.
In addition to the images the database includes 5,590 answer files, one for
each image. Each answer file contains an ASCII representation of the data found
in the entry fields on the corresponding image. Image format documentation and
example software are also provided.
The uncompressed database totals approximately 5.9 gigabytes of data.
"NIST Special Database 2" has the following features:
+ 5,590 full-page images
+ 5,590 answer files
+ 12 pixel per millimeter resolution
+ image format documentation and example software
Suitable for automated document processing system research and development, the
database can be used for:
+ algorithm development
+ system training and testing
The system requirements are a 5.25" CD-ROM drive with software to read ISO-9660
format.
If you have any further technical questions please contact:
Darrin L. Dimmick
dld@magi.ncsl.nist.gov
(301)975-4147
If you wish to order the database, please contact:
Standard Reference Data
National Institute of Standards and Technology
221/A323
Gaithersburg, MD 20899
(301)975-2208
(301)926-0416 (FAX)
------------------------------
Date: Mon, 20 Apr 92 09:44:09 EDT
From: Craig Watson <craig@magi.ncsl.nist.gov>
Organization: National Institute of Standards and Technology
formerly National Bureau of Standards
Subject: NIST Special Database 4: 8-Bit Images of Fingerprint Image Groups (FIGS)
NATIONAL INSTITUTE OF STANDARDS AND TECHNOLOGY
Announces a New Database
+-----------------------------+
| "NIST Special Database 4" |
+-----------------------------+
8-Bit Gray Scale Images of Fingerprint Image Groups
(FIGS)
The NIST database of fingerprint images contains 2000 8-bit gray scale
fingerprint image pairs. Each image is 512 by 512 pixels with 32 rows of
white space at the bottom and classified using one of the five following
classes: A=Arch, L=Left Loop, R=Right Loop, T=Tented Arch, W=Whirl. The
database is evenly distributed over each of the five classifications with
400 fingerprint pairs from each class. The images are compressed using a
modified JPEG lossless compression algorithm and require approximately
636 Megabytes of storage compressed and 1.1 Gigabytes uncompressed
(1.6 : 1 compression ratio). The database also includes format
documentation and example software.
"NIST Special Database 4" has the following features:
o 2000 8-bit gray scale fingerprint image pairs including
classifications
o 400 fingerprint pairs from each of the five classifications Arch,
Left and Right Loops, Tented Arch, Whirl
o each of the fingerprint pairs are two completely different
rollings of the same fingerprint
o 19.6850 pixels per millimeter resolution
o image format documentation and example software
Suitable for automated fingerprint classification research, the database
can be used for:
o algorithm development
o system training and testing
The database is a valuable tool for evaluating fingerprint systems on a
statistical sample of fingerprints which is evenly distributed over the
five major classifications. The system requirements are a 5.25" CD-ROM
drive with software to read ISO-9660 format.
If you have any further technical questions please contact:
Craig I. Watson
craig@magi.ncsl.nist.gov
(301)975-4402
If you wish to order the database, please contact:
Standard Reference Data
National Institute of Standards and Technology
Bldg. 221/A323
Gaithersburg, MD 20899
(301)975-2208
(301)926-0416 (FAX)
------------------------------
Date: Fri, 17 Apr 92 16:27:02 GMT
From: samsung!ulowell!pixel.cps.msu.edu!dulimart@uunet.UU.NET (Hansye S. Dulimarta)
Organization: Department of Computer Science, Michigan State University
Subject: Stereo Camera Calibration.
Dear netters,
I've been thinking about this binocular stereo problem:
Given:
(1) Calibration matrices of both cameras.
(2) A set of 3D points whose relative coordinates are known.
(3) The correspondence of points in both images.
Is it possible to recover the *baseline* and/or *orientation* of both
cameras. [I'm also assuming that both optical axis are in the same
plane.]
If somebody could give me references regarding this subject, I
appreciate it very much.
Hans.
------------------------------
Date: 20 Apr 1992 17:42:46 GMT
From: srik@uirvlj.csl.uiuc.edu (Srikanth Thirumalai)
Organization: Center for Reliable and High-Performance Computing, University of Illinois at Urbana-Champaign
Subject: image sequence needed
I need a sequence of images (around 15) with the following specifications -
* 2 or more objects moving independently.
* Ground truth for all objects must be known.
* Motion of objects should be around 3-4 pixels.
* Objects should be sufficiently textured for optical flow estimation.
* Image centers should be known exactly.
* Focus setting of the camera and other relevant camera parameters needed
to estimate motion and structure must be known.
If any of the netters have such a sequence I would appreciate it if they
could let me know where I could get it.
Thanks.
Srikanth Thirumalai.
------------------------------
Date: Fri, 17 Apr 1992 20:59:39 GMT
From: holder@cse.uta.edu (Larry Holder)
Organization: Computer Science & Engineering, Univ. of Texas at Arlington
Subject: Looking for Relational Datasets
We are looking for data to be used for testing an intelligent
relational data analysis tool that looks for repetitive structure in
the relational data. Ideally, the data would be described in terms of
relations. An example would be visual scenes described at a high
level in terms of the objects present (e.g., shape(object1,square),
color(object1,red), etc.) and the relationships between these objects
(e.g., distance(obj1,obj2,10), left-of, on-top, next-to, connects,
etc.). We have had some success converting images to line-drawings
and then into a relational Waltz-label representation, so images
displaying repetitive structure would also be acceptable. Any
pointers to such data sets would be appreciated.
Thanks.
Larry Holder (holder@cse.uta.edu)
University of Texas at Arlington, Department of Computer Science Engineering
Box 19015, Arlington, TX 76019-0015, Phone: 817-273-2596, FAX: 817-273-2548
------------------------------
Date: Fri, 17 Apr 92 21:23:25 EDT
From: pankanti@cps.msu.edu (Jonathan D. Courtney)
Subject: Parallel Partitional Clustering
I am looking for some info(references) on the parallel implement-
ations of partitional clustering algorithm ( like CLUSTER, ISODATA,
FORGY) in recent years(say, after 1984).
Thank you,
------------------------------
Date: 19 Apr 92 17:13:00 GMT
From: Robin Allenson <robina@castle.ed.ac.uk>
Organization: Edinburgh University
Subject: info wanted on curve descriptions
Keywords: machine vision, AI, boundary, curves, splines, Bezier, Fourier,
linear regression, symbolic description
I am doing some research on how to translate a list of boundary points
of a shape into a more symbolic description. At present I have worked
out the algorithm to locate the ends of straight segments (which was
very simple), as well as a way describing circular curves (I can
derive the radius of curvature and the centre from any three points).
Does anyone have any references, or could anyone tell me, how to
describe curves more generally. For instance, what are splines (cubic
or otherwise) or Bezier curves? Is it possible to use Fourier series
here? Least squares regression?
The method I will use will depend strongly on the fact that I am
working in Prolog, and am using a _list_ of points, that is, a list of
(x,y) pairs. Hence, I feel that a method that needs random access to
points is probably going about it the wrong way (for this application
anyway). Ideally, I'd like to be able to move through the list from
beginning to end, reporting on the segments I've found and describing
what type they are, with some characteristics, as I move through.
eg. "straight segment from [21,40] to [47,84],
Bezier curve with parameters <...> from [48,84] to [100,60]..." and so on
We can assume that the list of points is connected by a line with no
breaks. Most of the shapes whose boundaries we will be using will be
of the order of 100x100 pixels in size.
Any ideas would be gratefully received. If there is sufficient
response by email, I will post a summary. Whatever I receive, I'll
send a summary of finished project (whenever it does get finished!).
Thanks,
Robin Allenson
robina@uk.ac.ed.castle Conflict is usually
robin@uk.ac.ed.cogsci egoic.
------------------------------
Date: Mon, 20 Apr 1992 01:29:34 GMT
From: krishna@suliman.iss.nus.sg (Krishnamoorthy Subrahmanyam)
Organization: Institute of Systems Science, NUS, Singapore
Subject: LAS ALAMOS NATIONAL LAB : Enquiry
Hi,
We, the group of researchers in ISS, Singapore, interested to know about and
willing to communicate the group in LOS ALAMOS NATIONAL LAB, USA, which
comprises
Lolheim, Inger
Tanya L.Payne
Palph H.Castan
and wish to get their paper on "The Potential of using backprobagation neural
networks for facial recognition".
We don't have their e-mail account and we will appreciate your help in this
regard.
We are doing a project on Face photofit, recognition and aging.
Thanks in advance.
...Krishnamoorthy.
krishna @ iss.nus.sg
------------------------------
End of VISION-LIST digest 11.15
************************
