Word separation of unconstrained handwritten text lines in PCR forms

Ifeoma Nwogu; Gyeonghwan Kim

doi:10.1109/ICDAR.2005.255

Word separation of unconstrained handwritten text lines in PCR forms

Ifeoma Nwogu
, Gyeonghwan Kim

Department of Computer Science and Engineering

Sogang University

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

Abstract

An approach for segmenting handwritten text in a Pre-Hospital Care Report (PCR) is presented. Segmentation of lines and words in a PCR is extremely challenging due to the nature of the environment in which the reports are created, giving rise to low quality, poorly written, loosely constrained data. Stroke analyses are performed and image primitives are extracted for word detection. A heuristics-based approach, involving gap spacing, height transitions, and the average stroke width of the writer is used in detecting word boundaries. Carbon copies of live PCRs are used for testing. Experiments show perfect segmentation of 69%, outperforming the more tested and proven algorithms by as much as 15%.

Original language	English
Title of host publication	Proceedings of the Eighth International Conference on Document Analysis and Recognition
Publisher	IEEE Computer Society
Pages	715-719
Number of pages	5
ISBN (Print)	0769524206, 9780769524207
DOIs	https://doi.org/10.1109/ICDAR.2005.255
State	Published - 2005
Event	8th International Conference on Document Analysis and Recognition, ICDAR 2005 - Seoul, Korea, Republic of Duration: Aug 31 2005 → Sep 1 2005

Publication series

Name	Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volume	2005
ISSN (Print)	1520-5363

Conference

Conference	8th International Conference on Document Analysis and Recognition, ICDAR 2005
Country/Territory	Korea, Republic of
City	Seoul
Period	08/31/05 → 09/1/05

Access to Document

10.1109/ICDAR.2005.255

Cite this

Nwogu, I., & Kim, G. (2005). Word separation of unconstrained handwritten text lines in PCR forms. In Proceedings of the Eighth International Conference on Document Analysis and Recognition (pp. 715-719). Article 1575638 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 2005). IEEE Computer Society. https://doi.org/10.1109/ICDAR.2005.255

@inproceedings{f72bc02a88614d60974ab061ac7ec3e4,

title = "Word separation of unconstrained handwritten text lines in PCR forms",

abstract = "An approach for segmenting handwritten text in a Pre-Hospital Care Report (PCR) is presented. Segmentation of lines and words in a PCR is extremely challenging due to the nature of the environment in which the reports are created, giving rise to low quality, poorly written, loosely constrained data. Stroke analyses are performed and image primitives are extracted for word detection. A heuristics-based approach, involving gap spacing, height transitions, and the average stroke width of the writer is used in detecting word boundaries. Carbon copies of live PCRs are used for testing. Experiments show perfect segmentation of 69\%, outperforming the more tested and proven algorithms by as much as 15\%.",

author = "Ifeoma Nwogu and Gyeonghwan Kim",

year = "2005",

doi = "10.1109/ICDAR.2005.255",

language = "English",

isbn = "0769524206",

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

publisher = "IEEE Computer Society",

pages = "715--719",

booktitle = "Proceedings of the Eighth International Conference on Document Analysis and Recognition",

address = "United States",

note = " 8th International Conference on Document Analysis and Recognition, ICDAR 2005 ; Conference date: 31-08-2005 Through 01-09-2005",

}

Nwogu, I & Kim, G 2005, Word separation of unconstrained handwritten text lines in PCR forms. in Proceedings of the Eighth International Conference on Document Analysis and Recognition., 1575638, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, vol. 2005, IEEE Computer Society, pp. 715-719, 8th International Conference on Document Analysis and Recognition, ICDAR 2005, Seoul, Korea, Republic of, 08/31/05. https://doi.org/10.1109/ICDAR.2005.255

Word separation of unconstrained handwritten text lines in PCR forms. / Nwogu, Ifeoma; Kim, Gyeonghwan.
Proceedings of the Eighth International Conference on Document Analysis and Recognition. IEEE Computer Society, 2005. p. 715-719 1575638 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 2005).

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

TY - GEN

T1 - Word separation of unconstrained handwritten text lines in PCR forms

AU - Nwogu, Ifeoma

AU - Kim, Gyeonghwan

PY - 2005

Y1 - 2005

N2 - An approach for segmenting handwritten text in a Pre-Hospital Care Report (PCR) is presented. Segmentation of lines and words in a PCR is extremely challenging due to the nature of the environment in which the reports are created, giving rise to low quality, poorly written, loosely constrained data. Stroke analyses are performed and image primitives are extracted for word detection. A heuristics-based approach, involving gap spacing, height transitions, and the average stroke width of the writer is used in detecting word boundaries. Carbon copies of live PCRs are used for testing. Experiments show perfect segmentation of 69%, outperforming the more tested and proven algorithms by as much as 15%.

AB - An approach for segmenting handwritten text in a Pre-Hospital Care Report (PCR) is presented. Segmentation of lines and words in a PCR is extremely challenging due to the nature of the environment in which the reports are created, giving rise to low quality, poorly written, loosely constrained data. Stroke analyses are performed and image primitives are extracted for word detection. A heuristics-based approach, involving gap spacing, height transitions, and the average stroke width of the writer is used in detecting word boundaries. Carbon copies of live PCRs are used for testing. Experiments show perfect segmentation of 69%, outperforming the more tested and proven algorithms by as much as 15%.

UR - https://www.scopus.com/pages/publications/33947365553

U2 - 10.1109/ICDAR.2005.255

DO - 10.1109/ICDAR.2005.255

M3 - Conference contribution

AN - SCOPUS:33947365553

SN - 0769524206

SN - 9780769524207

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

SP - 715

EP - 719

BT - Proceedings of the Eighth International Conference on Document Analysis and Recognition

PB - IEEE Computer Society

T2 - 8th International Conference on Document Analysis and Recognition, ICDAR 2005

Y2 - 31 August 2005 through 1 September 2005

ER -

Word separation of unconstrained handwritten text lines in PCR forms

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this