Fast algorithm for character line extraction from handwritten examination papers

Katsunari Goto, Chinthaka Premachandra, Shinji Tsuruoka, Haruhiko Takase, Hiroharu Kawanaka

研究成果: Conference contribution

抄録

Academic institutions such as universities and technical colleges usually conduct paper-based examinations and reports for evaluating students' academic performance. Teachers must take considerable time for paper marking in the paper-based examinations. To reduce the paper marking burden of the teachers, we are developing an automatic paper marking system. To execute paper marking, handwritten character lines are extracted from examination papers, and then characters on those lines are recognized. In this paper, we mainly discuss about the character line extraction from handwritten examination papers without ruled line. The extraction of character lines from the non-ruled papers is difficult through image processing due to the writing characteristic of the students. Furthermore, extraction accuracy becomes an important factor for the character recognition performance. The conventional character line extraction algorithms for printed document does not show better performance for this problem. At the beginning of this study, we propose a method combining two conventional methods. But, it took a dozens of seconds to implementation. Thus, in this paper we develop a new method having better performance in character line extraction and processing time reduction.

元の言語English
ホスト出版物のタイトル2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014
出版者Institute of Electrical and Electronics Engineers Inc.
ページ1454-1458
ページ数5
ISBN(印刷物)9781479959556
DOI
出版物ステータスPublished - 2014 2 18
外部発表Yes
イベント2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014 - Kitakyushu, Japan
継続期間: 2014 12 32014 12 6

Other

Other2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014
Japan
Kitakyushu
期間14/12/314/12/6

Fingerprint

Students
Character recognition
Image processing
Processing

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

これを引用

Goto, K., Premachandra, C., Tsuruoka, S., Takase, H., & Kawanaka, H. (2014). Fast algorithm for character line extraction from handwritten examination papers. : 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014 (pp. 1454-1458). [7044733] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SCIS-ISIS.2014.7044733

Fast algorithm for character line extraction from handwritten examination papers. / Goto, Katsunari; Premachandra, Chinthaka; Tsuruoka, Shinji; Takase, Haruhiko; Kawanaka, Hiroharu.

2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1454-1458 7044733.

研究成果: Conference contribution

Goto, K, Premachandra, C, Tsuruoka, S, Takase, H & Kawanaka, H 2014, Fast algorithm for character line extraction from handwritten examination papers. : 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014., 7044733, Institute of Electrical and Electronics Engineers Inc., pp. 1454-1458, 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014, Kitakyushu, Japan, 14/12/3. https://doi.org/10.1109/SCIS-ISIS.2014.7044733
Goto K, Premachandra C, Tsuruoka S, Takase H, Kawanaka H. Fast algorithm for character line extraction from handwritten examination papers. : 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 1454-1458. 7044733 https://doi.org/10.1109/SCIS-ISIS.2014.7044733
Goto, Katsunari ; Premachandra, Chinthaka ; Tsuruoka, Shinji ; Takase, Haruhiko ; Kawanaka, Hiroharu. / Fast algorithm for character line extraction from handwritten examination papers. 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 1454-1458
@inproceedings{129184b7b1ae41d6963cff211c2df573,
title = "Fast algorithm for character line extraction from handwritten examination papers",
abstract = "Academic institutions such as universities and technical colleges usually conduct paper-based examinations and reports for evaluating students' academic performance. Teachers must take considerable time for paper marking in the paper-based examinations. To reduce the paper marking burden of the teachers, we are developing an automatic paper marking system. To execute paper marking, handwritten character lines are extracted from examination papers, and then characters on those lines are recognized. In this paper, we mainly discuss about the character line extraction from handwritten examination papers without ruled line. The extraction of character lines from the non-ruled papers is difficult through image processing due to the writing characteristic of the students. Furthermore, extraction accuracy becomes an important factor for the character recognition performance. The conventional character line extraction algorithms for printed document does not show better performance for this problem. At the beginning of this study, we propose a method combining two conventional methods. But, it took a dozens of seconds to implementation. Thus, in this paper we develop a new method having better performance in character line extraction and processing time reduction.",
keywords = "character line, document analysis, examination paper, thinning algorithm",
author = "Katsunari Goto and Chinthaka Premachandra and Shinji Tsuruoka and Haruhiko Takase and Hiroharu Kawanaka",
year = "2014",
month = "2",
day = "18",
doi = "10.1109/SCIS-ISIS.2014.7044733",
language = "English",
isbn = "9781479959556",
pages = "1454--1458",
booktitle = "2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Fast algorithm for character line extraction from handwritten examination papers

AU - Goto, Katsunari

AU - Premachandra, Chinthaka

AU - Tsuruoka, Shinji

AU - Takase, Haruhiko

AU - Kawanaka, Hiroharu

PY - 2014/2/18

Y1 - 2014/2/18

N2 - Academic institutions such as universities and technical colleges usually conduct paper-based examinations and reports for evaluating students' academic performance. Teachers must take considerable time for paper marking in the paper-based examinations. To reduce the paper marking burden of the teachers, we are developing an automatic paper marking system. To execute paper marking, handwritten character lines are extracted from examination papers, and then characters on those lines are recognized. In this paper, we mainly discuss about the character line extraction from handwritten examination papers without ruled line. The extraction of character lines from the non-ruled papers is difficult through image processing due to the writing characteristic of the students. Furthermore, extraction accuracy becomes an important factor for the character recognition performance. The conventional character line extraction algorithms for printed document does not show better performance for this problem. At the beginning of this study, we propose a method combining two conventional methods. But, it took a dozens of seconds to implementation. Thus, in this paper we develop a new method having better performance in character line extraction and processing time reduction.

AB - Academic institutions such as universities and technical colleges usually conduct paper-based examinations and reports for evaluating students' academic performance. Teachers must take considerable time for paper marking in the paper-based examinations. To reduce the paper marking burden of the teachers, we are developing an automatic paper marking system. To execute paper marking, handwritten character lines are extracted from examination papers, and then characters on those lines are recognized. In this paper, we mainly discuss about the character line extraction from handwritten examination papers without ruled line. The extraction of character lines from the non-ruled papers is difficult through image processing due to the writing characteristic of the students. Furthermore, extraction accuracy becomes an important factor for the character recognition performance. The conventional character line extraction algorithms for printed document does not show better performance for this problem. At the beginning of this study, we propose a method combining two conventional methods. But, it took a dozens of seconds to implementation. Thus, in this paper we develop a new method having better performance in character line extraction and processing time reduction.

KW - character line

KW - document analysis

KW - examination paper

KW - thinning algorithm

UR - http://www.scopus.com/inward/record.url?scp=84946530856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946530856&partnerID=8YFLogxK

U2 - 10.1109/SCIS-ISIS.2014.7044733

DO - 10.1109/SCIS-ISIS.2014.7044733

M3 - Conference contribution

AN - SCOPUS:84946530856

SN - 9781479959556

SP - 1454

EP - 1458

BT - 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems, SCIS 2014 and 15th International Symposium on Advanced Intelligent Systems, ISIS 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -