A fast line extraction method based on basic segment grouping

Balázs Tusor, A. Várkonyi-Kóczy, József Bukor

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

Abstract

Finding straight lines on images is a regularly occurring problem in fields of science that include image processing. In this paper, a new method is proposed that is capable of extracting lines from images. It uses a bottom-up approach: finding small (3-pixels long) lines on the edge map, analyzing and grouping them based on their derived characteristics. From the groups, the appropriate straight lines can be easily determined. The main advantage of this method is that most of its functionalities can be done with parallel computing, thus achieving a very fast operation.

Original languageEnglish
Title of host publicationI2MTC 2018 - 2018 IEEE International Instrumentation and Measurement Technology Conference
Subtitle of host publicationDiscovering New Horizons in Instrumentation and Measurement, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
ISBN (Electronic)9781538622223
DOIs
Publication statusPublished - Jul 10 2018
Event2018 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2018 - Houston, United States
Duration: May 14 2018May 17 2018

Other

Other2018 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2018
CountryUnited States
CityHouston
Period5/14/185/17/18

Fingerprint

Parallel processing systems
Image processing
Pixels
image processing
pixels

Keywords

  • bottom-up approach
  • Canny edge detection
  • Hough line transform
  • image processing
  • indexing tables
  • line detection
  • line extraction
  • parallel computing
  • signal processing

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Instrumentation

Cite this

Tusor, B., Várkonyi-Kóczy, A., & Bukor, J. (2018). A fast line extraction method based on basic segment grouping. In I2MTC 2018 - 2018 IEEE International Instrumentation and Measurement Technology Conference: Discovering New Horizons in Instrumentation and Measurement, Proceedings (pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/I2MTC.2018.8409852

A fast line extraction method based on basic segment grouping. / Tusor, Balázs; Várkonyi-Kóczy, A.; Bukor, József.

I2MTC 2018 - 2018 IEEE International Instrumentation and Measurement Technology Conference: Discovering New Horizons in Instrumentation and Measurement, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6.

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

Tusor, B, Várkonyi-Kóczy, A & Bukor, J 2018, A fast line extraction method based on basic segment grouping. in I2MTC 2018 - 2018 IEEE International Instrumentation and Measurement Technology Conference: Discovering New Horizons in Instrumentation and Measurement, Proceedings. Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 2018 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2018, Houston, United States, 5/14/18. https://doi.org/10.1109/I2MTC.2018.8409852
Tusor B, Várkonyi-Kóczy A, Bukor J. A fast line extraction method based on basic segment grouping. In I2MTC 2018 - 2018 IEEE International Instrumentation and Measurement Technology Conference: Discovering New Horizons in Instrumentation and Measurement, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6 https://doi.org/10.1109/I2MTC.2018.8409852
Tusor, Balázs ; Várkonyi-Kóczy, A. ; Bukor, József. / A fast line extraction method based on basic segment grouping. I2MTC 2018 - 2018 IEEE International Instrumentation and Measurement Technology Conference: Discovering New Horizons in Instrumentation and Measurement, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-6
@inproceedings{4291bbaec844409582e50751c3dca4d1,
title = "A fast line extraction method based on basic segment grouping",
abstract = "Finding straight lines on images is a regularly occurring problem in fields of science that include image processing. In this paper, a new method is proposed that is capable of extracting lines from images. It uses a bottom-up approach: finding small (3-pixels long) lines on the edge map, analyzing and grouping them based on their derived characteristics. From the groups, the appropriate straight lines can be easily determined. The main advantage of this method is that most of its functionalities can be done with parallel computing, thus achieving a very fast operation.",
keywords = "bottom-up approach, Canny edge detection, Hough line transform, image processing, indexing tables, line detection, line extraction, parallel computing, signal processing",
author = "Bal{\'a}zs Tusor and A. V{\'a}rkonyi-K{\'o}czy and J{\'o}zsef Bukor",
year = "2018",
month = "7",
day = "10",
doi = "10.1109/I2MTC.2018.8409852",
language = "English",
pages = "1--6",
booktitle = "I2MTC 2018 - 2018 IEEE International Instrumentation and Measurement Technology Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A fast line extraction method based on basic segment grouping

AU - Tusor, Balázs

AU - Várkonyi-Kóczy, A.

AU - Bukor, József

PY - 2018/7/10

Y1 - 2018/7/10

N2 - Finding straight lines on images is a regularly occurring problem in fields of science that include image processing. In this paper, a new method is proposed that is capable of extracting lines from images. It uses a bottom-up approach: finding small (3-pixels long) lines on the edge map, analyzing and grouping them based on their derived characteristics. From the groups, the appropriate straight lines can be easily determined. The main advantage of this method is that most of its functionalities can be done with parallel computing, thus achieving a very fast operation.

AB - Finding straight lines on images is a regularly occurring problem in fields of science that include image processing. In this paper, a new method is proposed that is capable of extracting lines from images. It uses a bottom-up approach: finding small (3-pixels long) lines on the edge map, analyzing and grouping them based on their derived characteristics. From the groups, the appropriate straight lines can be easily determined. The main advantage of this method is that most of its functionalities can be done with parallel computing, thus achieving a very fast operation.

KW - bottom-up approach

KW - Canny edge detection

KW - Hough line transform

KW - image processing

KW - indexing tables

KW - line detection

KW - line extraction

KW - parallel computing

KW - signal processing

UR - http://www.scopus.com/inward/record.url?scp=85050734602&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050734602&partnerID=8YFLogxK

U2 - 10.1109/I2MTC.2018.8409852

DO - 10.1109/I2MTC.2018.8409852

M3 - Conference contribution

AN - SCOPUS:85050734602

SP - 1

EP - 6

BT - I2MTC 2018 - 2018 IEEE International Instrumentation and Measurement Technology Conference

PB - Institute of Electrical and Electronics Engineers Inc.

ER -