Evolution maps for connected components in text documents

Ofer Biller; Klara Kedem; Itshak Dinstein; Jihad El-Sana

doi:10.1109/ICFHR.2012.201

Evolution maps for connected components in text documents

Ofer Biller, Klara Kedem, Itshak Dinstein, Jihad El-Sana

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

5 Scopus citations

Abstract

For highly degraded text documents, common tasks such as binarization and line extraction, remain difficult tasks. Equipped with a reliable information regarding the distribution of character dimensions in the document, one can improve results of these algorithms significantly. We introduce a novel perspective of the image data which maps the evolution of connected components along the change in gray scale threshold. We use these maps to provide a robust algorithm for extracting information about character dimensions in degraded documents, and demonstrate improvement in binarization results using this information. We analyze statistically the characteristics of the evolution maps for text documents, and compare our results with ground truth data.

Original language	English
Title of host publication	Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012
Pages	405-410
Number of pages	6
DOIs	https://doi.org/10.1109/ICFHR.2012.201
State	Published - 1 Dec 2012
Event	13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012 - Bari, Italy Duration: 18 Sep 2012 → 20 Sep 2012

Publication series

Name	Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR
ISSN (Print)	1550-5235

Conference

Conference	13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012
Country/Territory	Italy
City	Bari
Period	18/09/12 → 20/09/12

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICFHR.2012.201

Cite this

Biller, O., Kedem, K., Dinstein, I., & El-Sana, J. (2012). Evolution maps for connected components in text documents. In Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012 (pp. 405-410). Article 6424427 (Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR). https://doi.org/10.1109/ICFHR.2012.201

@inproceedings{02021ead68ab4b8387d3600ac106ecd2,

title = "Evolution maps for connected components in text documents",

abstract = "For highly degraded text documents, common tasks such as binarization and line extraction, remain difficult tasks. Equipped with a reliable information regarding the distribution of character dimensions in the document, one can improve results of these algorithms significantly. We introduce a novel perspective of the image data which maps the evolution of connected components along the change in gray scale threshold. We use these maps to provide a robust algorithm for extracting information about character dimensions in degraded documents, and demonstrate improvement in binarization results using this information. We analyze statistically the characteristics of the evolution maps for text documents, and compare our results with ground truth data.",

author = "Ofer Biller and Klara Kedem and Itshak Dinstein and Jihad El-Sana",

year = "2012",

month = dec,

day = "1",

doi = "10.1109/ICFHR.2012.201",

language = "English",

isbn = "9780769547749",

series = "Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR",

pages = "405--410",

booktitle = "Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012",

note = "13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012 ; Conference date: 18-09-2012 Through 20-09-2012",

}

Biller, O, Kedem, K , Dinstein, I & El-Sana, J 2012, Evolution maps for connected components in text documents. in Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012., 6424427, Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR, pp. 405-410, 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012, Bari, Italy, 18/09/12. https://doi.org/10.1109/ICFHR.2012.201

Evolution maps for connected components in text documents. / Biller, Ofer; Kedem, Klara ; Dinstein, Itshak et al.
Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012. 2012. p. 405-410 6424427 (Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR).

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

TY - GEN

T1 - Evolution maps for connected components in text documents

AU - Biller, Ofer

AU - Kedem, Klara

AU - Dinstein, Itshak

AU - El-Sana, Jihad

PY - 2012/12/1

Y1 - 2012/12/1

N2 - For highly degraded text documents, common tasks such as binarization and line extraction, remain difficult tasks. Equipped with a reliable information regarding the distribution of character dimensions in the document, one can improve results of these algorithms significantly. We introduce a novel perspective of the image data which maps the evolution of connected components along the change in gray scale threshold. We use these maps to provide a robust algorithm for extracting information about character dimensions in degraded documents, and demonstrate improvement in binarization results using this information. We analyze statistically the characteristics of the evolution maps for text documents, and compare our results with ground truth data.

AB - For highly degraded text documents, common tasks such as binarization and line extraction, remain difficult tasks. Equipped with a reliable information regarding the distribution of character dimensions in the document, one can improve results of these algorithms significantly. We introduce a novel perspective of the image data which maps the evolution of connected components along the change in gray scale threshold. We use these maps to provide a robust algorithm for extracting information about character dimensions in degraded documents, and demonstrate improvement in binarization results using this information. We analyze statistically the characteristics of the evolution maps for text documents, and compare our results with ground truth data.

UR - http://www.scopus.com/inward/record.url?scp=84874286595&partnerID=8YFLogxK

U2 - 10.1109/ICFHR.2012.201

DO - 10.1109/ICFHR.2012.201

M3 - Conference contribution

AN - SCOPUS:84874286595

SN - 9780769547749

T3 - Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR

SP - 405

EP - 410

BT - Proceedings - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012

T2 - 13th International Conference on Frontiers in Handwriting Recognition, ICFHR 2012

Y2 - 18 September 2012 through 20 September 2012

ER -

Evolution maps for connected components in text documents

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this