Message-Id: <mailto:199603281701.LAA19968@library.wustl.edu> Date: Thu, 28 Mar 1996 09:59:36 -0800 From: Stuart Glogoff <mailto:sglogoff@BIRD.LIBRARY.ARIZONA.EDU> Subject: Indexing Handwriting presentation at ACM/DL'96 To: Multiple recipients of list IMAGELIB
Last week I had to opportunity to attend the Association for Computing Machinery<ACM)/Digital Libraries '96 conference in Bethesda, Maryland. The conference was an interesting mix of reports on research projects in information science and current digital library projects.One session that I thought would be particularly interesting to IMAGELIB'ers was "Indexing Handwriting Using Word Matching," by R. Manmatha, Chengfeng Han, E. M. Riseman, and W.B. Croft, from the Center for Intelligent Information Retrieval, Computer Science Dept., U. Mass, Amherst, MA 01003. Principal author's email was listed as mailto:manmatha@cs.umass.edu. Here's the abstract:
"There are many historical manuscripts written in a single hand which it would be useful to index. Examples include the W.B. DuBois collection at the U of Mass and the early Presidential libraries at the Lib of Congress. The standard technique for indexing documents is to scan them in, convert them to machine readable form (ASCII) using Optical Character Recognition (OCR) and then index them using a text retrieval engine. However, OCR does not work well on handwriting. Here an alternative scheme is proposed for indexing such texts. Each page of the document is segmented into words. The images of the words are then matched against each other to create equivalence classes (each equivalence classes contains multiple instances of the same word). The user then provides ASCII equivalents for say the top 2000 equivalence classes.
"The current paper deals with the matching aspects of this process. Due to variations in even a single person's handwriting, it is expected that the matching will be the most difficult step in the whole process. A matching technique based on Euclidean distance mapping is discussed. Experiments are shown demonstrating the feasibility of the approach."
p. 151 Proceedings of the 1st ACM International Conference on Digital Libraries.
I've linked a brief summary with a scanned version of the TOC to my homepage, if you're interested. I also added some links to some of the projects and working sessions that were given. URL---> http://www.library.arizona.edu/users/sglogoff/dl96.html.
Regards, Stuart
********************************************************************** Stuart Glogoff | Asst Dean, Library Information Sys | A302 Main Library | mailto:sglogoff@bird.library.arizona.edu 1510 E. University Blvd. | University of Arizona | Voice: (520) 621-6433 Tucson, AZ 85720-0055 | FAX: (520) 621-9733 ***********************************************************************