Broken character restoration using gradient vector flow and balloon force algorithm

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The presence of a large number of broken characters in a digital document image represents the main problem in Optical Character Recognition (OCR) of historical documents. This problem still continues a challenge for recent OCR solutions. Broken character restoration from historical documents it is substantial because these documents contain important facts and leaving them leads to losing invaluable information. Gradient Vector Flow (GVF) snake has much more capture range than traditional snake therefore widely used in image segmentation. In this paper we used balloon with triangle steps to improve GVF snake to converge of deep concavity area and Restore broken characters using the improved GVF.

Original languageEnglish
Pages (from-to)441-446
Number of pages6
JournalJournal of Theoretical and Applied Information Technology
Volume73
Issue number3
Publication statusPublished - 1 Mar 2015

Fingerprint

Gradient Vector Flow
Balloon
Snakes
Balloons
Restoration
Optical character recognition
Character Recognition
Concavity
Image segmentation
Image Segmentation
Triangle
Continue
Converge
Range of data
Character

Keywords

  • Balloon force
  • Deep concavity
  • Divergence
  • GVF
  • Snake algorithm

ASJC Scopus subject areas

  • Computer Science(all)
  • Theoretical Computer Science

Cite this

Broken character restoration using gradient vector flow and balloon force algorithm. / Mosa, Qusay O.; Nasrudin, Mohammad Faidzul.

In: Journal of Theoretical and Applied Information Technology, Vol. 73, No. 3, 01.03.2015, p. 441-446.

Research output: Contribution to journalArticle

@article{4eed12cb10004a1292f5d0d3ec699755,
title = "Broken character restoration using gradient vector flow and balloon force algorithm",
abstract = "The presence of a large number of broken characters in a digital document image represents the main problem in Optical Character Recognition (OCR) of historical documents. This problem still continues a challenge for recent OCR solutions. Broken character restoration from historical documents it is substantial because these documents contain important facts and leaving them leads to losing invaluable information. Gradient Vector Flow (GVF) snake has much more capture range than traditional snake therefore widely used in image segmentation. In this paper we used balloon with triangle steps to improve GVF snake to converge of deep concavity area and Restore broken characters using the improved GVF.",
keywords = "Balloon force, Deep concavity, Divergence, GVF, Snake algorithm",
author = "Mosa, {Qusay O.} and Nasrudin, {Mohammad Faidzul}",
year = "2015",
month = "3",
day = "1",
language = "English",
volume = "73",
pages = "441--446",
journal = "Journal of Theoretical and Applied Information Technology",
issn = "1992-8645",
publisher = "Asian Research Publishing Network (ARPN)",
number = "3",

}

TY - JOUR

T1 - Broken character restoration using gradient vector flow and balloon force algorithm

AU - Mosa, Qusay O.

AU - Nasrudin, Mohammad Faidzul

PY - 2015/3/1

Y1 - 2015/3/1

N2 - The presence of a large number of broken characters in a digital document image represents the main problem in Optical Character Recognition (OCR) of historical documents. This problem still continues a challenge for recent OCR solutions. Broken character restoration from historical documents it is substantial because these documents contain important facts and leaving them leads to losing invaluable information. Gradient Vector Flow (GVF) snake has much more capture range than traditional snake therefore widely used in image segmentation. In this paper we used balloon with triangle steps to improve GVF snake to converge of deep concavity area and Restore broken characters using the improved GVF.

AB - The presence of a large number of broken characters in a digital document image represents the main problem in Optical Character Recognition (OCR) of historical documents. This problem still continues a challenge for recent OCR solutions. Broken character restoration from historical documents it is substantial because these documents contain important facts and leaving them leads to losing invaluable information. Gradient Vector Flow (GVF) snake has much more capture range than traditional snake therefore widely used in image segmentation. In this paper we used balloon with triangle steps to improve GVF snake to converge of deep concavity area and Restore broken characters using the improved GVF.

KW - Balloon force

KW - Deep concavity

KW - Divergence

KW - GVF

KW - Snake algorithm

UR - http://www.scopus.com/inward/record.url?scp=84926154278&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926154278&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84926154278

VL - 73

SP - 441

EP - 446

JO - Journal of Theoretical and Applied Information Technology

JF - Journal of Theoretical and Applied Information Technology

SN - 1992-8645

IS - 3

ER -