Construction of Handwriting Databases Using Transcript-based Mapping

Bin Zhang; Catalin Tomai; Sargur Srihari; Venu Govindaraju

Construction of Handwriting Databases Using Transcript-based Mapping

Bin Zhang
, Catalin Tomai
, Sargur Srihari
, Venu Govindaraju

Research and Economic Development

University of California at Los Angeles
SUNY Buffalo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

A recognition-based system was developed for constructing handwriting databases. The system automatically recognizes the word and the character images in handwritten document images by applying a transcript mapping algorithm. The transcript-mapping process is modeled as an optimization problem involving multiple word-segmentation hypotheses, word recognition and word alignment. The extensive experiments show that a large number of character and word images can be automatically extracted with very high reliability.

Original language	English
Title of host publication	Proceedings First International Workshop on Document Image Analysis for Libraries - DIAL 2004
Pages	288-298
Number of pages	11
State	Published - 2004
Event	Proceedings First International Workshop on Document Image Analysis for Libraries DIAL 2004 - Palo Alto, CA, United States Duration: Jan 23 2004 → Jan 24 2004

Publication series

Name	Proceedings - First International Workshop on Document Image Analysis for Libraries - DIAL 2004

Conference

Conference	Proceedings First International Workshop on Document Image Analysis for Libraries DIAL 2004
Country/Territory	United States
City	Palo Alto, CA
Period	01/23/04 → 01/24/04

Cite this

@inproceedings{24cba07d0e514871870d0a48999f4976,

title = "Construction of Handwriting Databases Using Transcript-based Mapping",

abstract = "A recognition-based system was developed for constructing handwriting databases. The system automatically recognizes the word and the character images in handwritten document images by applying a transcript mapping algorithm. The transcript-mapping process is modeled as an optimization problem involving multiple word-segmentation hypotheses, word recognition and word alignment. The extensive experiments show that a large number of character and word images can be automatically extracted with very high reliability.",

author = "Bin Zhang and Catalin Tomai and Sargur Srihari and Venu Govindaraju",

year = "2004",

language = "English",

isbn = "076952088X",

series = "Proceedings - First International Workshop on Document Image Analysis for Libraries - DIAL 2004",

pages = "288--298",

booktitle = "Proceedings First International Workshop on Document Image Analysis for Libraries - DIAL 2004",

note = "Proceedings First International Workshop on Document Image Analysis for Libraries DIAL 2004 ; Conference date: 23-01-2004 Through 24-01-2004",

}

Zhang, B, Tomai, C, Srihari, S & Govindaraju, V 2004, Construction of Handwriting Databases Using Transcript-based Mapping. in Proceedings First International Workshop on Document Image Analysis for Libraries - DIAL 2004. Proceedings - First International Workshop on Document Image Analysis for Libraries - DIAL 2004, pp. 288-298, Proceedings First International Workshop on Document Image Analysis for Libraries DIAL 2004, Palo Alto, CA, United States, 01/23/04.

Construction of Handwriting Databases Using Transcript-based Mapping. / Zhang, Bin; Tomai, Catalin; Srihari, Sargur et al.
Proceedings First International Workshop on Document Image Analysis for Libraries - DIAL 2004. 2004. p. 288-298 (Proceedings - First International Workshop on Document Image Analysis for Libraries - DIAL 2004).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Construction of Handwriting Databases Using Transcript-based Mapping

AU - Zhang, Bin

AU - Tomai, Catalin

AU - Srihari, Sargur

AU - Govindaraju, Venu

PY - 2004

Y1 - 2004

N2 - A recognition-based system was developed for constructing handwriting databases. The system automatically recognizes the word and the character images in handwritten document images by applying a transcript mapping algorithm. The transcript-mapping process is modeled as an optimization problem involving multiple word-segmentation hypotheses, word recognition and word alignment. The extensive experiments show that a large number of character and word images can be automatically extracted with very high reliability.

AB - A recognition-based system was developed for constructing handwriting databases. The system automatically recognizes the word and the character images in handwritten document images by applying a transcript mapping algorithm. The transcript-mapping process is modeled as an optimization problem involving multiple word-segmentation hypotheses, word recognition and word alignment. The extensive experiments show that a large number of character and word images can be automatically extracted with very high reliability.

UR - https://www.scopus.com/pages/publications/1942516363

M3 - Conference contribution

AN - SCOPUS:1942516363

SN - 076952088X

SN - 9780769520889

T3 - Proceedings - First International Workshop on Document Image Analysis for Libraries - DIAL 2004

SP - 288

EP - 298

BT - Proceedings First International Workshop on Document Image Analysis for Libraries - DIAL 2004

T2 - Proceedings First International Workshop on Document Image Analysis for Libraries DIAL 2004

Y2 - 23 January 2004 through 24 January 2004

ER -

Construction of Handwriting Databases Using Transcript-based Mapping

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this