Character spotting using image-based stochastic models

Seon Kyu Kim; Bong Kee Sin; Seong Whan Lee

doi:10.1109/ICDAR.2001.953755

Character spotting using image-based stochastic models

Seon Kyu Kim, Bong Kee Sin, Seong Whan Lee

Department of Brain and Cognitive Engineering

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

1 Citation (Scopus)

Abstract

This paper concerns the modeling of character images by a Markov-like stochastic template that is constructed in the form of the pseudo 2D HMM. Being constructed directly from the image templates, the models can be composed in real time. Preliminary test results in digit recognition and Korean Hangul character spotting show the feasibility of the proposed method, especially in the context of incremental location of keywords.

Original language	English
Title of host publication	Proceedings - 6th International Conference on Document Analysis and Recognition, ICDAR 2001
Publisher	IEEE Computer Society
Pages	60-63
Number of pages	4
Volume	2001-January
ISBN (Electronic)	0769512631, 0769512631, 0769512631
DOIs	https://doi.org/10.1109/ICDAR.2001.953755
Publication status	Published - 2001
Event	6th International Conference on Document Analysis and Recognition, ICDAR 2001 - Seattle, United States Duration: 2001 Sep 10 → 2001 Sep 13

Other

Other	6th International Conference on Document Analysis and Recognition, ICDAR 2001
Country	United States
City	Seattle
Period	01/9/10 → 01/9/13

Fingerprint

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Cite this

Kim, S. K., Sin, B. K., & Lee, S. W. (2001). Character spotting using image-based stochastic models. In Proceedings - 6th International Conference on Document Analysis and Recognition, ICDAR 2001 (Vol. 2001-January, pp. 60-63). [953755] IEEE Computer Society. https://doi.org/10.1109/ICDAR.2001.953755

Kim, SK, Sin, BK & Lee, SW 2001, Character spotting using image-based stochastic models. in Proceedings - 6th International Conference on Document Analysis and Recognition, ICDAR 2001. vol. 2001-January, 953755, IEEE Computer Society, pp. 60-63, 6th International Conference on Document Analysis and Recognition, ICDAR 2001, Seattle, United States, 01/9/10. https://doi.org/10.1109/ICDAR.2001.953755

@inproceedings{1d5e7023524b4cdb93d3e1b045674334,

title = "Character spotting using image-based stochastic models",

abstract = "This paper concerns the modeling of character images by a Markov-like stochastic template that is constructed in the form of the pseudo 2D HMM. Being constructed directly from the image templates, the models can be composed in real time. Preliminary test results in digit recognition and Korean Hangul character spotting show the feasibility of the proposed method, especially in the context of incremental location of keywords.",

author = "Kim, {Seon Kyu} and Sin, {Bong Kee} and Lee, {Seong Whan}",

year = "2001",

doi = "10.1109/ICDAR.2001.953755",

language = "English",

volume = "2001-January",

pages = "60--63",

booktitle = "Proceedings - 6th International Conference on Document Analysis and Recognition, ICDAR 2001",

publisher = "IEEE Computer Society",

note = "6th International Conference on Document Analysis and Recognition, ICDAR 2001 ; Conference date: 10-09-2001 Through 13-09-2001",

}

TY - GEN

T1 - Character spotting using image-based stochastic models

AU - Kim, Seon Kyu

AU - Sin, Bong Kee

AU - Lee, Seong Whan

PY - 2001

Y1 - 2001

N2 - This paper concerns the modeling of character images by a Markov-like stochastic template that is constructed in the form of the pseudo 2D HMM. Being constructed directly from the image templates, the models can be composed in real time. Preliminary test results in digit recognition and Korean Hangul character spotting show the feasibility of the proposed method, especially in the context of incremental location of keywords.

AB - This paper concerns the modeling of character images by a Markov-like stochastic template that is constructed in the form of the pseudo 2D HMM. Being constructed directly from the image templates, the models can be composed in real time. Preliminary test results in digit recognition and Korean Hangul character spotting show the feasibility of the proposed method, especially in the context of incremental location of keywords.

UR - http://www.scopus.com/inward/record.url?scp=84942508888&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942508888&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2001.953755

DO - 10.1109/ICDAR.2001.953755

M3 - Conference contribution

AN - SCOPUS:84942508888

VL - 2001-January

SP - 60

EP - 63

BT - Proceedings - 6th International Conference on Document Analysis and Recognition, ICDAR 2001

PB - IEEE Computer Society

T2 - 6th International Conference on Document Analysis and Recognition, ICDAR 2001

Y2 - 10 September 2001 through 13 September 2001

ER -

Access to Document

10.1109/ICDAR.2001.953755