A FAST LEXICALLY CONSTRAINED VITERBI ALGORITHM FOR ON­ LINE HANDWRITING RECOGNITIO

A. Lifchitz; F. Maire

A FAST LEXICALLY CONSTRAINED VITERBI ALGORITHM FOR ON LINE HANDWRITING RECOGNITIO

A. Lifchitz
, F. Maire

University of Groningen

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

167 Downloads (Pure)

Abstract

Most online cursive handwriting recognition systems use a lexical constraint to help improve the recognition performance. Traditionally, the vocabulary lexicon is stored in a trie (automaton whose underlying graph is a tree). In this paper, we propose a solution based on a more compact data structure, the directed acyclic word graph (DAWG). We show that our solution is equivalent to the traditional system. Moreover, we propose a number of heuristics to reduce the size of the DAWG and present experimental results demonstrating a significant improvement.

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-041-lifchitz.pdfFinal publisher's version, 68.2 KB

Handle.net

Persistent link

Cite this

@inproceedings{1b10cae6e0bd40f78f5a834211a73c9a,

title = "A FAST LEXICALLY CONSTRAINED VITERBI ALGORITHM FOR ON LINE HANDWRITING RECOGNITIO",

abstract = "Most online cursive handwriting recognition systems use a lexical constraint to help improve the recognition performance. Traditionally, the vocabulary lexicon is stored in a trie (automaton whose underlying graph is a tree). In this paper, we propose a solution based on a more compact data structure, the directed acyclic word graph (DAWG). We show that our solution is equivalent to the traditional system. Moreover, we propose a number of heuristics to reduce the size of the DAWG and present experimental results demonstrating a significant improvement.",

author = "A. Lifchitz and F. Maire",

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

year = "2004",

language = "English",

booktitle = "EPRINTS-BOOK-TITLE",

publisher = "s.n.",

}

TY - GEN

T1 - A FAST LEXICALLY CONSTRAINED VITERBI ALGORITHM FOR ON LINE HANDWRITING RECOGNITIO

AU - Lifchitz, A.

AU - Maire, F.

N1 - date_submitted:2004 Rights: University of Groningen

PY - 2004

Y1 - 2004

N2 - Most online cursive handwriting recognition systems use a lexical constraint to help improve the recognition performance. Traditionally, the vocabulary lexicon is stored in a trie (automaton whose underlying graph is a tree). In this paper, we propose a solution based on a more compact data structure, the directed acyclic word graph (DAWG). We show that our solution is equivalent to the traditional system. Moreover, we propose a number of heuristics to reduce the size of the DAWG and present experimental results demonstrating a significant improvement.

AB - Most online cursive handwriting recognition systems use a lexical constraint to help improve the recognition performance. Traditionally, the vocabulary lexicon is stored in a trie (automaton whose underlying graph is a tree). In this paper, we propose a solution based on a more compact data structure, the directed acyclic word graph (DAWG). We show that our solution is equivalent to the traditional system. Moreover, we propose a number of heuristics to reduce the size of the DAWG and present experimental results demonstrating a significant improvement.

M3 - Conference contribution

BT - EPRINTS-BOOK-TITLE

PB - s.n.

ER -