A two-stage binarization approach for document images

Zheru Chi; K. W. Wong

A two-stage binarization approach for document images

Zheru Chi, K. W. Wong

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

19 Citations (Scopus)

Abstract

Binarization of a gray scale document image is one of the most important steps for automatic documentprocessing. This papev presents a two-stage document image binarization approach. The approach applies a region-based binarization technique first to the whole image and utilizes a neural network based binarization technique to those text blocks in which a good character segmentation cannot be achieved at the first stage. Experimental results on a number of document images show that our two-stage binarization approach performs better than other binarization techniques in terms of character segmentation quality and computing time.

Original language	English
Title of host publication	Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2001
Pages	275-278
Number of pages	4
Publication status	Published - 1 Dec 2001
Event	2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2001 - Hong Kong, Hong Kong Duration: 2 May 2001 → 4 May 2001

Conference

Conference	2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2001
Country/Territory	Hong Kong
City	Hong Kong
Period	2/05/01 → 4/05/01

ASJC Scopus subject areas

General Computer Science

Cite this

@inproceedings{37e765a927c94393a93f2b6cbc492495,

title = "A two-stage binarization approach for document images",

abstract = "Binarization of a gray scale document image is one of the most important steps for automatic documentprocessing. This papev presents a two-stage document image binarization approach. The approach applies a region-based binarization technique first to the whole image and utilizes a neural network based binarization technique to those text blocks in which a good character segmentation cannot be achieved at the first stage. Experimental results on a number of document images show that our two-stage binarization approach performs better than other binarization techniques in terms of character segmentation quality and computing time.",

author = "Zheru Chi and Wong, {K. W.}",

year = "2001",

month = dec,

day = "1",

language = "English",

isbn = "9628576623",

pages = "275--278",

booktitle = "Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2001",

note = "2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2001 ; Conference date: 02-05-2001 Through 04-05-2001",

}

TY - GEN

T1 - A two-stage binarization approach for document images

AU - Chi, Zheru

AU - Wong, K. W.

PY - 2001/12/1

Y1 - 2001/12/1

N2 - Binarization of a gray scale document image is one of the most important steps for automatic documentprocessing. This papev presents a two-stage document image binarization approach. The approach applies a region-based binarization technique first to the whole image and utilizes a neural network based binarization technique to those text blocks in which a good character segmentation cannot be achieved at the first stage. Experimental results on a number of document images show that our two-stage binarization approach performs better than other binarization techniques in terms of character segmentation quality and computing time.

AB - Binarization of a gray scale document image is one of the most important steps for automatic documentprocessing. This papev presents a two-stage document image binarization approach. The approach applies a region-based binarization technique first to the whole image and utilizes a neural network based binarization technique to those text blocks in which a good character segmentation cannot be achieved at the first stage. Experimental results on a number of document images show that our two-stage binarization approach performs better than other binarization techniques in terms of character segmentation quality and computing time.

UR - http://www.scopus.com/inward/record.url?scp=13344256890&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SN - 9628576623

SN - 9789628576623

SP - 275

EP - 278

BT - Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2001

T2 - 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, ISIMP 2001

Y2 - 2 May 2001 through 4 May 2001

ER -

A two-stage binarization approach for document images

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this