A full English sentence database for off-line handwriting recognition

Author

Marti, U.-V. ; Bunke, H.

Author_Institution

Inst. fur Inf., Bern Univ., Switzerland

fYear

1999

fDate

20-22 Sep 1999

Firstpage

705

Lastpage

708

Abstract

We present a new database for off-line handwriting recognition, together with a few preprocessing and text segmentation procedures. The database is based on the Lancaster-Oslo/Bergen(LOB) corpus. This corpus is a collection of tests that were used to generate forms, which subsequently were filled out by persons in their own handwriting. As of December 1998 the database includes 556 forms produced by approximately 250 different writers. The database consists of full English sentences. It could serve as a basis for a variety of handwriting recognition tasks. The main focus, however is on recognition techniques that use linguistic knowledge beyond the lexicon level. This knowledge can be automatically derived from the corpus or it can be supplied from external sources

Keywords

computational linguistics; handwriting recognition; English sentence database; Lancaster-Oslo/Bergen corpus; linguistic knowledge; off-line handwriting recognition; preprocessing; text segmentation; Character recognition; Databases; Handwriting recognition; Informatics; Mathematics; NIST; Optical character recognition software; Read only memory; Speech recognition; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference on

Conference_Location

Bangalore

Print_ISBN

0-7695-0318-7

Type

conf

DOI

10.1109/ICDAR.1999.791885

Filename

791885