Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images

Graham Leedham; Chen Yan; Kalyan Takru; Joie Hadi Nata Tan; Li Mian

doi:10.1109/ICDAR.2003.1227784

Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images

Graham Leedham
, Chen Yan
, Kalyan Takru
, Joie Hadi Nata Tan
, Li Mian

Computer Science

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

112 Citations (Scopus)

Abstract

A number of techniques have previously been proposed for effective thresholding of document images. In this paper two new thresholding techniques are proposed and compared against some existing algorithms. The algorithms were evaluated on four types of difficult document images where considerable background noise or variation in contrast and illumination exists. The quality of the thresholding was assessed using the Precision and Recall analysis of the resultant words in the foreground.The conclusion is that no single algorithm works well for all types of image but some work better than others for particular types of images suggesting that improved performance can be obtained by automatic selection or combination of appropriate algorithm(s) for the type of document image under investigation.

Original language	English
Title of host publication	Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003)
Place of Publication	United States of America
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	859-863
Volume	2
ISBN (Print)	0769519601
DOIs	https://doi.org/10.1109/ICDAR.2003.1227784
Publication status	Published - 2003
Event	ICDAR 2003: 7th International Conference of Document Analysis and Recognition - Edinburgh, United Kingdom Duration: 3 Aug 2003 → 6 Aug 2003

Conference

Conference	ICDAR 2003: 7th International Conference of Document Analysis and Recognition
City	Edinburgh, United Kingdom
Period	3/08/03 → 6/08/03

Keywords

Artificial Intelligence and Image Processing
Image Processing
Computer Vision

Access to Document

10.1109/ICDAR.2003.1227784

https://hdl.handle.net/1959.11/6619

Handle.net

Persistent link

Cite this

Leedham, G., Yan, C., Takru, K., Tan, J. H. N., & Mian, L. (2003). Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images. In Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003) (Vol. 2, pp. 859-863). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICDAR.2003.1227784

Leedham, Graham ; Yan, Chen ; Takru, Kalyan et al. / Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images. Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003). Vol. 2 United States of America : Institute of Electrical and Electronics Engineers (IEEE), 2003. pp. 859-863

@inproceedings{fb6c103437b84f9db46b5f95e61a24c2,

title = "Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images",

abstract = "A number of techniques have previously been proposed for effective thresholding of document images. In this paper two new thresholding techniques are proposed and compared against some existing algorithms. The algorithms were evaluated on four types of difficult document images where considerable background noise or variation in contrast and illumination exists. The quality of the thresholding was assessed using the Precision and Recall analysis of the resultant words in the foreground.The conclusion is that no single algorithm works well for all types of image but some work better than others for particular types of images suggesting that improved performance can be obtained by automatic selection or combination of appropriate algorithm(s) for the type of document image under investigation.",

keywords = "Artificial Intelligence and Image Processing, Image Processing, Computer Vision",

author = "Graham Leedham and Chen Yan and Kalyan Takru and Tan, \{Joie Hadi Nata\} and Li Mian",

year = "2003",

doi = "10.1109/ICDAR.2003.1227784",

language = "English",

isbn = "0769519601",

volume = "2",

pages = "859--863",

booktitle = "Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

note = "ICDAR 2003: 7th International Conference of Document Analysis and Recognition ; Conference date: 03-08-2003 Through 06-08-2003",

}

Leedham, G, Yan, C, Takru, K, Tan, JHN & Mian, L 2003, Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images. in Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003). vol. 2, Institute of Electrical and Electronics Engineers (IEEE), United States of America, pp. 859-863, ICDAR 2003: 7th International Conference of Document Analysis and Recognition, Edinburgh, United Kingdom, 3/08/03. https://doi.org/10.1109/ICDAR.2003.1227784

Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images. / Leedham, Graham; Yan, Chen; Takru, Kalyan et al.
Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003). Vol. 2 United States of America: Institute of Electrical and Electronics Engineers (IEEE), 2003. p. 859-863.

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

TY - GEN

T1 - Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images

AU - Leedham, Graham

AU - Yan, Chen

AU - Takru, Kalyan

AU - Tan, Joie Hadi Nata

AU - Mian, Li

PY - 2003

Y1 - 2003

N2 - A number of techniques have previously been proposed for effective thresholding of document images. In this paper two new thresholding techniques are proposed and compared against some existing algorithms. The algorithms were evaluated on four types of difficult document images where considerable background noise or variation in contrast and illumination exists. The quality of the thresholding was assessed using the Precision and Recall analysis of the resultant words in the foreground.The conclusion is that no single algorithm works well for all types of image but some work better than others for particular types of images suggesting that improved performance can be obtained by automatic selection or combination of appropriate algorithm(s) for the type of document image under investigation.

AB - A number of techniques have previously been proposed for effective thresholding of document images. In this paper two new thresholding techniques are proposed and compared against some existing algorithms. The algorithms were evaluated on four types of difficult document images where considerable background noise or variation in contrast and illumination exists. The quality of the thresholding was assessed using the Precision and Recall analysis of the resultant words in the foreground.The conclusion is that no single algorithm works well for all types of image but some work better than others for particular types of images suggesting that improved performance can be obtained by automatic selection or combination of appropriate algorithm(s) for the type of document image under investigation.

KW - Artificial Intelligence and Image Processing

KW - Image Processing

KW - Computer Vision

UR - http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.99.9442&rep=rep1&type=pdf

U2 - 10.1109/ICDAR.2003.1227784

DO - 10.1109/ICDAR.2003.1227784

M3 - Conference contribution

SN - 0769519601

VL - 2

SP - 859

EP - 863

BT - Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - United States of America

T2 - ICDAR 2003: 7th International Conference of Document Analysis and Recognition

Y2 - 3 August 2003 through 6 August 2003

ER -

Leedham G, Yan C, Takru K, Tan JHN, Mian L. Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images. In Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003). Vol. 2. United States of America: Institute of Electrical and Electronics Engineers (IEEE). 2003. p. 859-863 doi: 10.1109/ICDAR.2003.1227784

Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this