Speed-up ellipse enclosing character detection approach for large-size document images by parallel scanning and Hough transform

H. Waruna H Premachandra, Chinthaka Premachandra, Chandana Dinesh Parape, Hiroharu Kawanaka

Research output: Contribution to journalArticle

  • 1 Citations

Abstract

This paper presents a speed-up ellipse enclosing character detection algorithm that uses parallel image scanning and the Hough transform (HT) for large-size document images. Objects in images are generally detected based on geometrical information obtained via raster scanning. In raster scanning, all pixels of an image are scanned starting from the upper-left point and ending with the lower-right point. In the case of large-size images, considerable time is needed for processing an image by scanning all pixels. In this paper, an object detection approach for large-size images is proposed which does not require scanning all pixels in the images. In this speed-up ellipse enclosing character detection approach for large-size document images, pixels are scanned on constantly spaced vertical parallel lines. If an object larger than a certain size is identified while scanning, the presence of an ellipse enclosing character is assumed and ellipse detection is conducted by applying HT only in a defined local image area over the found object. With this approach, processing time can be dramatically reduced by disregarding some objects and reducing the total image area used for ellipse detection.

LanguageEnglish
Pages371-378
Number of pages8
JournalInternational Journal of Machine Learning and Cybernetics
Volume8
Issue number1
DOIs
StatePublished - 2017 Feb 1
Externally publishedYes

Fingerprint

Hough transforms
Scanning
Pixels
Image processing
Processing

Keywords

  • Document image
  • Ellipse detection
  • Hough transform
  • Parallel pixel scanning
  • Speed-up image processing

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Speed-up ellipse enclosing character detection approach for large-size document images by parallel scanning and Hough transform. / Premachandra, H. Waruna H; Premachandra, Chinthaka; Parape, Chandana Dinesh; Kawanaka, Hiroharu.

In: International Journal of Machine Learning and Cybernetics, Vol. 8, No. 1, 01.02.2017, p. 371-378.

Research output: Contribution to journalArticle

@article{7df2fb98f7db4364b8239e606f6399e6,
title = "Speed-up ellipse enclosing character detection approach for large-size document images by parallel scanning and Hough transform",
abstract = "This paper presents a speed-up ellipse enclosing character detection algorithm that uses parallel image scanning and the Hough transform (HT) for large-size document images. Objects in images are generally detected based on geometrical information obtained via raster scanning. In raster scanning, all pixels of an image are scanned starting from the upper-left point and ending with the lower-right point. In the case of large-size images, considerable time is needed for processing an image by scanning all pixels. In this paper, an object detection approach for large-size images is proposed which does not require scanning all pixels in the images. In this speed-up ellipse enclosing character detection approach for large-size document images, pixels are scanned on constantly spaced vertical parallel lines. If an object larger than a certain size is identified while scanning, the presence of an ellipse enclosing character is assumed and ellipse detection is conducted by applying HT only in a defined local image area over the found object. With this approach, processing time can be dramatically reduced by disregarding some objects and reducing the total image area used for ellipse detection.",
keywords = "Document image, Ellipse detection, Hough transform, Parallel pixel scanning, Speed-up image processing",
author = "Premachandra, {H. Waruna H} and Chinthaka Premachandra and Parape, {Chandana Dinesh} and Hiroharu Kawanaka",
year = "2017",
month = "2",
day = "1",
doi = "10.1007/s13042-015-0330-0",
language = "English",
volume = "8",
pages = "371--378",
journal = "International Journal of Machine Learning and Cybernetics",
issn = "1868-8071",
publisher = "Springer Science + Business Media",
number = "1",

}

TY - JOUR

T1 - Speed-up ellipse enclosing character detection approach for large-size document images by parallel scanning and Hough transform

AU - Premachandra,H. Waruna H

AU - Premachandra,Chinthaka

AU - Parape,Chandana Dinesh

AU - Kawanaka,Hiroharu

PY - 2017/2/1

Y1 - 2017/2/1

N2 - This paper presents a speed-up ellipse enclosing character detection algorithm that uses parallel image scanning and the Hough transform (HT) for large-size document images. Objects in images are generally detected based on geometrical information obtained via raster scanning. In raster scanning, all pixels of an image are scanned starting from the upper-left point and ending with the lower-right point. In the case of large-size images, considerable time is needed for processing an image by scanning all pixels. In this paper, an object detection approach for large-size images is proposed which does not require scanning all pixels in the images. In this speed-up ellipse enclosing character detection approach for large-size document images, pixels are scanned on constantly spaced vertical parallel lines. If an object larger than a certain size is identified while scanning, the presence of an ellipse enclosing character is assumed and ellipse detection is conducted by applying HT only in a defined local image area over the found object. With this approach, processing time can be dramatically reduced by disregarding some objects and reducing the total image area used for ellipse detection.

AB - This paper presents a speed-up ellipse enclosing character detection algorithm that uses parallel image scanning and the Hough transform (HT) for large-size document images. Objects in images are generally detected based on geometrical information obtained via raster scanning. In raster scanning, all pixels of an image are scanned starting from the upper-left point and ending with the lower-right point. In the case of large-size images, considerable time is needed for processing an image by scanning all pixels. In this paper, an object detection approach for large-size images is proposed which does not require scanning all pixels in the images. In this speed-up ellipse enclosing character detection approach for large-size document images, pixels are scanned on constantly spaced vertical parallel lines. If an object larger than a certain size is identified while scanning, the presence of an ellipse enclosing character is assumed and ellipse detection is conducted by applying HT only in a defined local image area over the found object. With this approach, processing time can be dramatically reduced by disregarding some objects and reducing the total image area used for ellipse detection.

KW - Document image

KW - Ellipse detection

KW - Hough transform

KW - Parallel pixel scanning

KW - Speed-up image processing

UR - http://www.scopus.com/inward/record.url?scp=85011396336&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011396336&partnerID=8YFLogxK

U2 - 10.1007/s13042-015-0330-0

DO - 10.1007/s13042-015-0330-0

M3 - Article

VL - 8

SP - 371

EP - 378

JO - International Journal of Machine Learning and Cybernetics

T2 - International Journal of Machine Learning and Cybernetics

JF - International Journal of Machine Learning and Cybernetics

SN - 1868-8071

IS - 1

ER -