Cooperative text and line-art extraction from a topographic map

Luyang Li, George Nagy, Ashok K Samal, Sharad Seth, Yihong Xu

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

13 Citations (Scopus)

Abstract

The black layer is digitized from a USGS topographic map digitized at 1000 dpi. The connected components of this layer are analyzed and separated into line art, text, and icons in two passes. The paired street casings are converted to polylines by vectorization and associated with street labels from the character recognition phase. The accuracy of character recognition is shown to improve by taking account of the frequently occurring overlap of line art with street labels. The experiments show that complete vectorization of the black line-layer bitmap is the major remaining problem.

Original languageEnglish (US)
Title of host publicationProceedings of the 5th International Conference on Document Analysis and Recognition, ICDAR 1999
PublisherIEEE Computer Society
Pages471-474
Number of pages4
ISBN (Electronic)0769503187
DOIs
StatePublished - Jan 1 1999
Event5th International Conference on Document Analysis and Recognition, ICDAR 1999 - Bangalore, India
Duration: Sep 20 1999Sep 22 1999

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
ISSN (Print)1520-5363

Other

Other5th International Conference on Document Analysis and Recognition, ICDAR 1999
CountryIndia
CityBangalore
Period9/20/999/22/99

Fingerprint

Character recognition
Labels
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Li, L., Nagy, G., Samal, A. K., Seth, S., & Xu, Y. (1999). Cooperative text and line-art extraction from a topographic map. In Proceedings of the 5th International Conference on Document Analysis and Recognition, ICDAR 1999 (pp. 471-474). [791826] (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). IEEE Computer Society. https://doi.org/10.1109/ICDAR.1999.791826

Cooperative text and line-art extraction from a topographic map. / Li, Luyang; Nagy, George; Samal, Ashok K; Seth, Sharad; Xu, Yihong.

Proceedings of the 5th International Conference on Document Analysis and Recognition, ICDAR 1999. IEEE Computer Society, 1999. p. 471-474 791826 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR).

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

Li, L, Nagy, G, Samal, AK, Seth, S & Xu, Y 1999, Cooperative text and line-art extraction from a topographic map. in Proceedings of the 5th International Conference on Document Analysis and Recognition, ICDAR 1999., 791826, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, IEEE Computer Society, pp. 471-474, 5th International Conference on Document Analysis and Recognition, ICDAR 1999, Bangalore, India, 9/20/99. https://doi.org/10.1109/ICDAR.1999.791826
Li L, Nagy G, Samal AK, Seth S, Xu Y. Cooperative text and line-art extraction from a topographic map. In Proceedings of the 5th International Conference on Document Analysis and Recognition, ICDAR 1999. IEEE Computer Society. 1999. p. 471-474. 791826. (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). https://doi.org/10.1109/ICDAR.1999.791826
Li, Luyang ; Nagy, George ; Samal, Ashok K ; Seth, Sharad ; Xu, Yihong. / Cooperative text and line-art extraction from a topographic map. Proceedings of the 5th International Conference on Document Analysis and Recognition, ICDAR 1999. IEEE Computer Society, 1999. pp. 471-474 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR).
@inproceedings{3f00961e124545ae8db9463476a8e9b7,
title = "Cooperative text and line-art extraction from a topographic map",
abstract = "The black layer is digitized from a USGS topographic map digitized at 1000 dpi. The connected components of this layer are analyzed and separated into line art, text, and icons in two passes. The paired street casings are converted to polylines by vectorization and associated with street labels from the character recognition phase. The accuracy of character recognition is shown to improve by taking account of the frequently occurring overlap of line art with street labels. The experiments show that complete vectorization of the black line-layer bitmap is the major remaining problem.",
author = "Luyang Li and George Nagy and Samal, {Ashok K} and Sharad Seth and Yihong Xu",
year = "1999",
month = "1",
day = "1",
doi = "10.1109/ICDAR.1999.791826",
language = "English (US)",
series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
publisher = "IEEE Computer Society",
pages = "471--474",
booktitle = "Proceedings of the 5th International Conference on Document Analysis and Recognition, ICDAR 1999",

}

TY - GEN

T1 - Cooperative text and line-art extraction from a topographic map

AU - Li, Luyang

AU - Nagy, George

AU - Samal, Ashok K

AU - Seth, Sharad

AU - Xu, Yihong

PY - 1999/1/1

Y1 - 1999/1/1

N2 - The black layer is digitized from a USGS topographic map digitized at 1000 dpi. The connected components of this layer are analyzed and separated into line art, text, and icons in two passes. The paired street casings are converted to polylines by vectorization and associated with street labels from the character recognition phase. The accuracy of character recognition is shown to improve by taking account of the frequently occurring overlap of line art with street labels. The experiments show that complete vectorization of the black line-layer bitmap is the major remaining problem.

AB - The black layer is digitized from a USGS topographic map digitized at 1000 dpi. The connected components of this layer are analyzed and separated into line art, text, and icons in two passes. The paired street casings are converted to polylines by vectorization and associated with street labels from the character recognition phase. The accuracy of character recognition is shown to improve by taking account of the frequently occurring overlap of line art with street labels. The experiments show that complete vectorization of the black line-layer bitmap is the major remaining problem.

UR - http://www.scopus.com/inward/record.url?scp=34047217931&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34047217931&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.1999.791826

DO - 10.1109/ICDAR.1999.791826

M3 - Conference contribution

T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

SP - 471

EP - 474

BT - Proceedings of the 5th International Conference on Document Analysis and Recognition, ICDAR 1999

PB - IEEE Computer Society

ER -