Extraction of reference lines and items from form document images with complicated background

Dihua Xi, Seong Whan Lee

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The extraction of reference lines and items is a fundamental and crucial task in form document analysis. Most of the studies performed so far were done in connection with binary images. This paper proposes a method of extracting lines from gray-level images, by constructing a 2D pseudo Gaussian-Coiflet wavelet with adjustable rectangular support. We also present a method of extracting items using the extracted reference lines and multiresolution wavelet sub-images, which is independent of the intensity of the strokes and backgrounds. The experimental results demonstrate the effectiveness of our proposed methods.

Original languageEnglish
Pages (from-to)289-305
Number of pages17
JournalPattern Recognition
Volume38
Issue number2
DOIs
Publication statusPublished - 2005 Feb 1

Fingerprint

Binary images

Keywords

  • Form document analysis
  • Item extraction
  • Multiresolution decomposition
  • Reference line extraction
  • Wavelet

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Extraction of reference lines and items from form document images with complicated background. / Xi, Dihua; Lee, Seong Whan.

In: Pattern Recognition, Vol. 38, No. 2, 01.02.2005, p. 289-305.

Research output: Contribution to journalArticle

@article{8a17afb164b0478fa7c52792ba2b99cf,
title = "Extraction of reference lines and items from form document images with complicated background",
abstract = "The extraction of reference lines and items is a fundamental and crucial task in form document analysis. Most of the studies performed so far were done in connection with binary images. This paper proposes a method of extracting lines from gray-level images, by constructing a 2D pseudo Gaussian-Coiflet wavelet with adjustable rectangular support. We also present a method of extracting items using the extracted reference lines and multiresolution wavelet sub-images, which is independent of the intensity of the strokes and backgrounds. The experimental results demonstrate the effectiveness of our proposed methods.",
keywords = "Form document analysis, Item extraction, Multiresolution decomposition, Reference line extraction, Wavelet",
author = "Dihua Xi and Lee, {Seong Whan}",
year = "2005",
month = "2",
day = "1",
doi = "10.1016/j.patcog.2004.04.013",
language = "English",
volume = "38",
pages = "289--305",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "2",

}

TY - JOUR

T1 - Extraction of reference lines and items from form document images with complicated background

AU - Xi, Dihua

AU - Lee, Seong Whan

PY - 2005/2/1

Y1 - 2005/2/1

N2 - The extraction of reference lines and items is a fundamental and crucial task in form document analysis. Most of the studies performed so far were done in connection with binary images. This paper proposes a method of extracting lines from gray-level images, by constructing a 2D pseudo Gaussian-Coiflet wavelet with adjustable rectangular support. We also present a method of extracting items using the extracted reference lines and multiresolution wavelet sub-images, which is independent of the intensity of the strokes and backgrounds. The experimental results demonstrate the effectiveness of our proposed methods.

AB - The extraction of reference lines and items is a fundamental and crucial task in form document analysis. Most of the studies performed so far were done in connection with binary images. This paper proposes a method of extracting lines from gray-level images, by constructing a 2D pseudo Gaussian-Coiflet wavelet with adjustable rectangular support. We also present a method of extracting items using the extracted reference lines and multiresolution wavelet sub-images, which is independent of the intensity of the strokes and backgrounds. The experimental results demonstrate the effectiveness of our proposed methods.

KW - Form document analysis

KW - Item extraction

KW - Multiresolution decomposition

KW - Reference line extraction

KW - Wavelet

UR - http://www.scopus.com/inward/record.url?scp=6444226758&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=6444226758&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2004.04.013

DO - 10.1016/j.patcog.2004.04.013

M3 - Article

VL - 38

SP - 289

EP - 305

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 2

ER -