Message-Id: <mailto:199407151707.MAA02362@library.wustl.edu> Date: Fri, 15 Jul 1994 11:11:55 -0500 From: Jon Rudin <mailto:Rudin@MEDINFO.LABMED.UMN.EDU> Subject: Re: Image Vision To: Multiple recipients of list IMAGELIB <mailto:IMAGELIB@ARIZVM1.BITNET>
> Over the years at Kenyon, we have cataloged 50,000 of our slides and placed
> them into a database which we now find is useless as an end user retrieval
> system. Before we begin again, we need to give thought to the eventual goal,
> and plan to integrate our efforts into some national plan. Most our users of
> image colletions browse through our physical collections until they find what
> they want. In an electonic world, will thumbnail images work in the same way.
> Digital files are not arranged like our physical files.
>
> I sense that we have folks on this listserv from different communites. It
> would
> be good to hear the reactions to some of these issues.
>
> Any reactions?
>
>
> Paul M. Gherman
> Director of Libraries
> Olin and Chalmers Library
> Kenyon College
> Gamibier, OH 43022
> 614-427-5186 voice
> 614-427-2272 fax
> mailto:ghermanp@kenyon.edu
I worked on an image retrieval system as part of my master's program in Health Informatics. People at the VA created an electronic atlas on CD-ROM. It contains several hundred images of oral pathology (clinical oral manifestations of HIV infection). My contribution to the project was to create the taxonomy of descriptors for cataloging and retrieving the images. One of the main things I learned was that the list of descriptive terms must reflect how the end user will want to retrieve images. This guideline must be balanced with the potential difficulty for those cataloging the images.
For example, suppose an end user would like to retrieve an image of a man with a beard, appearing between 50 and 60 years old, looking slightly discouraged, with water in the background, a palm tree on the left side in the foreground, and with strong side lighting. Cataloging all these attributes may become tedious but still possible. Far more difficult would be a request for an image where the predominant color of the main subject, (e.g., a flower) is purple.
I don't know if my comments have helped or helped confuse. There are many other interesting things that came to light while working on this project. If anyone is interested, please feel free to contact me.
Thanks-
Jon
-----------------------------------------------------------------------------
Jonathan Rudin, DDS, MS
Post-doctoral fellow
Institute for Health Services Research University of Minnesota School of Public Health Box 729 420 Delaware St. SE Minneapolis, MN 55455
(612) 624-6151
Home: 1883 Yorkshire Ave., St. Paul, MN 55116; (612) 699-5472
E-mail: mailto:Rudin@MEDINFO.LABMED.umn.edu