Transcript mapping for handwritten text lines using conditional random fields

Xiang Dong Zhou; Fei Yin; Da Han Wang; Qiu Feng Wang; Masaki Nakagawa; Cheng Lin Liu

doi:10.1109/ICDAR.2011.21

Transcript mapping for handwritten text lines using conditional random fields

Xiang Dong Zhou^*, Fei Yin, Da Han Wang, Qiu Feng Wang, Masaki Nakagawa, Cheng Lin Liu

^*Corresponding author for this work

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

2 Citations (Scopus)

Abstract

This paper presents a conditional random field (CRF) model for aligning online handwritten Chinese/Japanese text lines (character strings) with the corresponding transcripts. The CRF model is defined on a lattice which contains all possible segmentation hypotheses. The feature functions characterize the shape and context dependences of characters, including the scores of character recognition and the geometric compatibilities between characters. The combining parameters are optimized by energy minimization. Experimental results on two online databases: CASIA-OLHWDB and TUAT Kondate demonstrate the effectiveness of the proposed method.

Original language	English
Title of host publication	Proceedings - 11th International Conference on Document Analysis and Recognition, ICDAR 2011
Pages	58-62
Number of pages	5
DOIs	https://doi.org/10.1109/ICDAR.2011.21
Publication status	Published - 2011
Externally published	Yes
Event	11th International Conference on Document Analysis and Recognition, ICDAR 2011 - Beijing, China Duration: 18 Sept 2011 → 21 Sept 2011

Publication series

Name	Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
ISSN (Print)	1520-5363

Conference

Conference	11th International Conference on Document Analysis and Recognition, ICDAR 2011
Country/Territory	China
City	Beijing
Period	18/09/11 → 21/09/11

Keywords

conditional random fields
text alignment
transcript mapping

Access to Document

10.1109/ICDAR.2011.21

Cite this

Zhou, X. D., Yin, F., Wang, D. H., Wang, Q. F., Nakagawa, M., & Liu, C. L. (2011). Transcript mapping for handwritten text lines using conditional random fields. In Proceedings - 11th International Conference on Document Analysis and Recognition, ICDAR 2011 (pp. 58-62). Article 6065276 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). https://doi.org/10.1109/ICDAR.2011.21

@inproceedings{56ae299c16a84a68874a8e30cb635070,

title = "Transcript mapping for handwritten text lines using conditional random fields",

abstract = "This paper presents a conditional random field (CRF) model for aligning online handwritten Chinese/Japanese text lines (character strings) with the corresponding transcripts. The CRF model is defined on a lattice which contains all possible segmentation hypotheses. The feature functions characterize the shape and context dependences of characters, including the scores of character recognition and the geometric compatibilities between characters. The combining parameters are optimized by energy minimization. Experimental results on two online databases: CASIA-OLHWDB and TUAT Kondate demonstrate the effectiveness of the proposed method.",

keywords = "conditional random fields, text alignment, transcript mapping",

author = "Zhou, {Xiang Dong} and Fei Yin and Wang, {Da Han} and Wang, {Qiu Feng} and Masaki Nakagawa and Liu, {Cheng Lin}",

year = "2011",

doi = "10.1109/ICDAR.2011.21",

language = "English",

isbn = "9780769545202",

series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",

pages = "58--62",

booktitle = "Proceedings - 11th International Conference on Document Analysis and Recognition, ICDAR 2011",

note = "11th International Conference on Document Analysis and Recognition, ICDAR 2011 ; Conference date: 18-09-2011 Through 21-09-2011",

}

Zhou, XD, Yin, F, Wang, DH, Wang, QF, Nakagawa, M & Liu, CL 2011, Transcript mapping for handwritten text lines using conditional random fields. in Proceedings - 11th International Conference on Document Analysis and Recognition, ICDAR 2011., 6065276, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, pp. 58-62, 11th International Conference on Document Analysis and Recognition, ICDAR 2011, Beijing, China, 18/09/11. https://doi.org/10.1109/ICDAR.2011.21

Transcript mapping for handwritten text lines using conditional random fields. / Zhou, Xiang Dong; Yin, Fei; Wang, Da Han et al.
Proceedings - 11th International Conference on Document Analysis and Recognition, ICDAR 2011. 2011. p. 58-62 6065276 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR).

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

TY - GEN

T1 - Transcript mapping for handwritten text lines using conditional random fields

AU - Zhou, Xiang Dong

AU - Yin, Fei

AU - Wang, Da Han

AU - Wang, Qiu Feng

AU - Nakagawa, Masaki

AU - Liu, Cheng Lin

PY - 2011

Y1 - 2011

N2 - This paper presents a conditional random field (CRF) model for aligning online handwritten Chinese/Japanese text lines (character strings) with the corresponding transcripts. The CRF model is defined on a lattice which contains all possible segmentation hypotheses. The feature functions characterize the shape and context dependences of characters, including the scores of character recognition and the geometric compatibilities between characters. The combining parameters are optimized by energy minimization. Experimental results on two online databases: CASIA-OLHWDB and TUAT Kondate demonstrate the effectiveness of the proposed method.

AB - This paper presents a conditional random field (CRF) model for aligning online handwritten Chinese/Japanese text lines (character strings) with the corresponding transcripts. The CRF model is defined on a lattice which contains all possible segmentation hypotheses. The feature functions characterize the shape and context dependences of characters, including the scores of character recognition and the geometric compatibilities between characters. The combining parameters are optimized by energy minimization. Experimental results on two online databases: CASIA-OLHWDB and TUAT Kondate demonstrate the effectiveness of the proposed method.

KW - conditional random fields

KW - text alignment

KW - transcript mapping

UR - http://www.scopus.com/inward/record.url?scp=82355190336&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2011.21

DO - 10.1109/ICDAR.2011.21

M3 - Conference Proceeding

AN - SCOPUS:82355190336

SN - 9780769545202

T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

SP - 58

EP - 62

BT - Proceedings - 11th International Conference on Document Analysis and Recognition, ICDAR 2011

T2 - 11th International Conference on Document Analysis and Recognition, ICDAR 2011

Y2 - 18 September 2011 through 21 September 2011

ER -

Zhou XD, Yin F, Wang DH, Wang QF, Nakagawa M, Liu CL. Transcript mapping for handwritten text lines using conditional random fields. In Proceedings - 11th International Conference on Document Analysis and Recognition, ICDAR 2011. 2011. p. 58-62. 6065276. (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). doi: 10.1109/ICDAR.2011.21

Transcript mapping for handwritten text lines using conditional random fields

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this