WORD LEXICON REDUCTION BY CHARACTER SPOTTING

D. Guilevic; D. Nishiwaki; K. Yamada

WORD LEXICON REDUCTION BY CHARACTER SPOTTING

D. Guilevic
, D. Nishiwaki
, K. Yamada

University of Groningen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic

165 Downloads (Pure)

Abstract

We describe a system, currently under development, to dynamically reduce a lexicon of city names, making use exclusively of the information found in a word image. Isolated characters are `spotted\\\' within the word. The recognition results on those isolated characters are then used to initialize a Hidden Markov Model (HMM) like module to dynamically reduce the lexicon.

Original language	English
Title of host publication	EPRINTS-BOOK-TITLE
Publisher	s.n.
Number of pages	10
Publication status	Published - 2004

Access to Document

paper-052-DidierGuillevic.pdfFinal publisher's version, 2.85 MB

Handle.net

Persistent link

Cite this

@inproceedings{98b7d06c87c14e9fbd35f05bef72a682,

title = "WORD LEXICON REDUCTION BY CHARACTER SPOTTING",

abstract = "We describe a system, currently under development, to dynamically reduce a lexicon of city names, making use exclusively of the information found in a word image. Isolated characters are `spotted\textbackslash{}\textbackslash{}\textbackslash{}' within the word. The recognition results on those isolated characters are then used to initialize a Hidden Markov Model (HMM) like module to dynamically reduce the lexicon.",

author = "D. Guilevic and D. Nishiwaki and K. Yamada",

note = "date\_submitted:2004 Rights: University of Groningen",

year = "2004",

language = "English",

booktitle = "EPRINTS-BOOK-TITLE",

publisher = "s.n.",

}

TY - GEN

T1 - WORD LEXICON REDUCTION BY CHARACTER SPOTTING

AU - Guilevic, D.

AU - Nishiwaki, D.

AU - Yamada, K.

N1 - date_submitted:2004 Rights: University of Groningen

PY - 2004

Y1 - 2004

N2 - We describe a system, currently under development, to dynamically reduce a lexicon of city names, making use exclusively of the information found in a word image. Isolated characters are `spotted\\\' within the word. The recognition results on those isolated characters are then used to initialize a Hidden Markov Model (HMM) like module to dynamically reduce the lexicon.

AB - We describe a system, currently under development, to dynamically reduce a lexicon of city names, making use exclusively of the information found in a word image. Isolated characters are `spotted\\\' within the word. The recognition results on those isolated characters are then used to initialize a Hidden Markov Model (HMM) like module to dynamically reduce the lexicon.

M3 - Conference contribution

BT - EPRINTS-BOOK-TITLE

PB - s.n.

ER -

WORD LEXICON REDUCTION BY CHARACTER SPOTTING

Abstract

Access to Document

Handle.net

Fingerprint

Cite this