Reference line extraction from form documents with complicated backgrounds

Dihua Xi, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Form document analysis is one of the most essential tasks in document analysis and recognition. One of the most fundamental and crucial tasks is the extraction of the reference lines which are contained in almost all form documents. This paper presents an efficient methodology for the complicated grey-level form image processing. We construct a non-orthogonal wavelet with adjustable rectangle supports and offer algorithms for the extraction of the reference lines based on the strip growth method using the multiresolution wavelet sub images. We have compared this system with the popular Hough transform (HT) based and the novel orthogonal wavelet based methods. As shown in the experiments, the proposed algorithmdemonstrates high performance and fast speed for the complicated form images. This system is also effective for the form images with slight skew.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Document Analysis and Recognition, ICDAR
PublisherIEEE Computer Society
Pages1080-1084
Number of pages5
Volume2003-January
ISBN (Print)0769519601
DOIs
Publication statusPublished - 2003
Event7th International Conference on Document Analysis and Recognition, ICDAR 2003 - Edinburgh, United Kingdom
Duration: 2003 Aug 32003 Aug 6

Other

Other7th International Conference on Document Analysis and Recognition, ICDAR 2003
CountryUnited Kingdom
CityEdinburgh
Period03/8/303/8/6

Fingerprint

Hough transforms
Image processing
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Xi, D., & Lee, S. W. (2003). Reference line extraction from form documents with complicated backgrounds. In Proceedings of the International Conference on Document Analysis and Recognition, ICDAR (Vol. 2003-January, pp. 1080-1084). [1227823] IEEE Computer Society. https://doi.org/10.1109/ICDAR.2003.1227823

Reference line extraction from form documents with complicated backgrounds. / Xi, Dihua; Lee, Seong Whan.

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. Vol. 2003-January IEEE Computer Society, 2003. p. 1080-1084 1227823.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xi, D & Lee, SW 2003, Reference line extraction from form documents with complicated backgrounds. in Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. vol. 2003-January, 1227823, IEEE Computer Society, pp. 1080-1084, 7th International Conference on Document Analysis and Recognition, ICDAR 2003, Edinburgh, United Kingdom, 03/8/3. https://doi.org/10.1109/ICDAR.2003.1227823
Xi D, Lee SW. Reference line extraction from form documents with complicated backgrounds. In Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. Vol. 2003-January. IEEE Computer Society. 2003. p. 1080-1084. 1227823 https://doi.org/10.1109/ICDAR.2003.1227823
Xi, Dihua ; Lee, Seong Whan. / Reference line extraction from form documents with complicated backgrounds. Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. Vol. 2003-January IEEE Computer Society, 2003. pp. 1080-1084
@inproceedings{c36bff2a348f4489a8438e32041999f5,
title = "Reference line extraction from form documents with complicated backgrounds",
abstract = "Form document analysis is one of the most essential tasks in document analysis and recognition. One of the most fundamental and crucial tasks is the extraction of the reference lines which are contained in almost all form documents. This paper presents an efficient methodology for the complicated grey-level form image processing. We construct a non-orthogonal wavelet with adjustable rectangle supports and offer algorithms for the extraction of the reference lines based on the strip growth method using the multiresolution wavelet sub images. We have compared this system with the popular Hough transform (HT) based and the novel orthogonal wavelet based methods. As shown in the experiments, the proposed algorithmdemonstrates high performance and fast speed for the complicated form images. This system is also effective for the form images with slight skew.",
author = "Dihua Xi and Lee, {Seong Whan}",
year = "2003",
doi = "10.1109/ICDAR.2003.1227823",
language = "English",
isbn = "0769519601",
volume = "2003-January",
pages = "1080--1084",
booktitle = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Reference line extraction from form documents with complicated backgrounds

AU - Xi, Dihua

AU - Lee, Seong Whan

PY - 2003

Y1 - 2003

N2 - Form document analysis is one of the most essential tasks in document analysis and recognition. One of the most fundamental and crucial tasks is the extraction of the reference lines which are contained in almost all form documents. This paper presents an efficient methodology for the complicated grey-level form image processing. We construct a non-orthogonal wavelet with adjustable rectangle supports and offer algorithms for the extraction of the reference lines based on the strip growth method using the multiresolution wavelet sub images. We have compared this system with the popular Hough transform (HT) based and the novel orthogonal wavelet based methods. As shown in the experiments, the proposed algorithmdemonstrates high performance and fast speed for the complicated form images. This system is also effective for the form images with slight skew.

AB - Form document analysis is one of the most essential tasks in document analysis and recognition. One of the most fundamental and crucial tasks is the extraction of the reference lines which are contained in almost all form documents. This paper presents an efficient methodology for the complicated grey-level form image processing. We construct a non-orthogonal wavelet with adjustable rectangle supports and offer algorithms for the extraction of the reference lines based on the strip growth method using the multiresolution wavelet sub images. We have compared this system with the popular Hough transform (HT) based and the novel orthogonal wavelet based methods. As shown in the experiments, the proposed algorithmdemonstrates high performance and fast speed for the complicated form images. This system is also effective for the form images with slight skew.

UR - http://www.scopus.com/inward/record.url?scp=9244223005&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=9244223005&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2003.1227823

DO - 10.1109/ICDAR.2003.1227823

M3 - Conference contribution

AN - SCOPUS:9244223005

SN - 0769519601

VL - 2003-January

SP - 1080

EP - 1084

BT - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

PB - IEEE Computer Society

ER -