Published June 1997
| Published
Book Section - Chapter
Open
Keyword spotting for cursive document retrieval
Abstract
We present one of the first attempts towards automatic retrieval of documents, in the noisy environment of unconstrained, multiple author handwritten forms. The documents were written in cursive script for which conventional OCR and text retrieval engines are not adequate. We focus on a visual word spotting indexing scheme for scanned documents housed in the Archives of the Indies in Seville, Spain. The framework presented utilizes pattern recognition, learning and information fusion methods, and is motivated from human word-spotting studies. The proposed system is described and initial results are presented.
Additional Information
© 1997 IEEE. We would like to thank Victoria Carmona Vergara of Seville, Spain, and Kanna Shimizu for their help in generating our database of documents. This work was supported in part by ARPA and ONR grant no. N00014093-1-0990, Patricia Keaton is supported by a Hughes Doctoral Fellowship, and Hayit Greenspan is supported in part by and Intel research grant.Attached Files
Published - 00627095.pdf
Files
00627095.pdf
Files
(787.2 kB)
Name | Size | Download all |
---|---|---|
md5:364d28afea63e1d429e0362b523aa48a
|
787.2 kB | Preview Download |
Additional details
- Eprint ID
- 95087
- Resolver ID
- CaltechAUTHORS:20190429-151824702
- Advanced Research Projects Agency (ARPA)
- N00014093-1-0990
- Office of Naval Research (ONR)
- Hughes Research Laboratories
- Intel
- Created
-
2019-04-29Created from EPrint's datestamp field
- Updated
-
2021-11-16Created from EPrint's last_modified field