An efficient method for document image geometric layout analysis

Suyoung Chi; Yunkoo Chung; Dae Geun Jang; Weongeun Oh; Jaeyeon Lee; Kim Changhun

An efficient method for document image geometric layout analysis

Suyoung Chi, Yunkoo Chung, Dae Geun Jang, Weongeun Oh, Jaeyeon Lee, Kim Changhun

Department of Computer Science and Engineering

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

Abstract

Document image analysis is necessary for optical character recognition (OCR) and also very useful for many other document image manipulations. In this paper, we propose a document image geometric layout analysis system which has less region segmentation and classification error than that of the commercial software and previous works. The proposed method segments the document image into small regions to the size of a character using fast connected components generation method, so that it prevents the different types of connected components from combining. We also propose new criterion for clustering the connected components and some new techniques to deal with noise and reduce computation time. Experiment shows classification error rate of text and picture regions is decreased.

Original language	English
Title of host publication	IASTED International Conference on Computer Graphics and Imaging
Editors	M.H. Hamza, M.H. Hamza
Pages	238-243
Number of pages	6
Publication status	Published - 2003
Event	Sixth IASTED International Conference on Computer Graphics and Imaging - Honolulu, HI, United States Duration: 2003 Aug 13 → 2003 Aug 15

Publication series

Name	IASTED International Conference on Computer Graphics and Imaging

Other

Other	Sixth IASTED International Conference on Computer Graphics and Imaging
Country	United States
City	Honolulu, HI
Period	03/8/13 → 03/8/15

Keywords

Connected Component Analysis
Document Image Analysis
Optical Character Recognition(OCR)

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design

Access to Document

Fingerprint Dive into the research topics of 'An efficient method for document image geometric layout analysis'. Together they form a unique fingerprint.

Cite this

An efficient method for document image geometric layout analysis. / Chi, Suyoung; Chung, Yunkoo; Jang, Dae Geun; Oh, Weongeun; Lee, Jaeyeon; Changhun, Kim.

IASTED International Conference on Computer Graphics and Imaging. ed. / M.H. Hamza; M.H. Hamza. 2003. p. 238-243 (IASTED International Conference on Computer Graphics and Imaging).

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

Chi, S, Chung, Y, Jang, DG, Oh, W, Lee, J & Changhun, K 2003, An efficient method for document image geometric layout analysis. in MH Hamza & MH Hamza (eds), IASTED International Conference on Computer Graphics and Imaging. IASTED International Conference on Computer Graphics and Imaging, pp. 238-243, Sixth IASTED International Conference on Computer Graphics and Imaging, Honolulu, HI, United States, 03/8/13.

@inproceedings{3a8ea2d03bf64038877240281302d232,

title = "An efficient method for document image geometric layout analysis",

abstract = "Document image analysis is necessary for optical character recognition (OCR) and also very useful for many other document image manipulations. In this paper, we propose a document image geometric layout analysis system which has less region segmentation and classification error than that of the commercial software and previous works. The proposed method segments the document image into small regions to the size of a character using fast connected components generation method, so that it prevents the different types of connected components from combining. We also propose new criterion for clustering the connected components and some new techniques to deal with noise and reduce computation time. Experiment shows classification error rate of text and picture regions is decreased.",

keywords = "Connected Component Analysis, Document Image Analysis, Optical Character Recognition(OCR)",

author = "Suyoung Chi and Yunkoo Chung and Jang, {Dae Geun} and Weongeun Oh and Jaeyeon Lee and Kim Changhun",

year = "2003",

language = "English",

isbn = "0889863768",

series = "IASTED International Conference on Computer Graphics and Imaging",

pages = "238--243",

editor = "M.H. Hamza and M.H. Hamza",

booktitle = "IASTED International Conference on Computer Graphics and Imaging",

note = "Sixth IASTED International Conference on Computer Graphics and Imaging ; Conference date: 13-08-2003 Through 15-08-2003",

}

TY - GEN

T1 - An efficient method for document image geometric layout analysis

AU - Chi, Suyoung

AU - Chung, Yunkoo

AU - Jang, Dae Geun

AU - Oh, Weongeun

AU - Lee, Jaeyeon

AU - Changhun, Kim

PY - 2003

Y1 - 2003

N2 - Document image analysis is necessary for optical character recognition (OCR) and also very useful for many other document image manipulations. In this paper, we propose a document image geometric layout analysis system which has less region segmentation and classification error than that of the commercial software and previous works. The proposed method segments the document image into small regions to the size of a character using fast connected components generation method, so that it prevents the different types of connected components from combining. We also propose new criterion for clustering the connected components and some new techniques to deal with noise and reduce computation time. Experiment shows classification error rate of text and picture regions is decreased.

AB - Document image analysis is necessary for optical character recognition (OCR) and also very useful for many other document image manipulations. In this paper, we propose a document image geometric layout analysis system which has less region segmentation and classification error than that of the commercial software and previous works. The proposed method segments the document image into small regions to the size of a character using fast connected components generation method, so that it prevents the different types of connected components from combining. We also propose new criterion for clustering the connected components and some new techniques to deal with noise and reduce computation time. Experiment shows classification error rate of text and picture regions is decreased.

KW - Connected Component Analysis

KW - Document Image Analysis

KW - Optical Character Recognition(OCR)

UR - http://www.scopus.com/inward/record.url?scp=1542359455&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542359455&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:1542359455

SN - 0889863768

T3 - IASTED International Conference on Computer Graphics and Imaging

SP - 238

EP - 243

BT - IASTED International Conference on Computer Graphics and Imaging

A2 - Hamza, M.H.

T2 - Sixth IASTED International Conference on Computer Graphics and Imaging

Y2 - 13 August 2003 through 15 August 2003

ER -