A Three-step Technique of Robust Line Detection with Modified Hough Transform

Huijun Di; Lei Wang; Guangyou Xu

doi:10.1117/12.538699

A Three-step Technique of Robust Line Detection with Modified Hough Transform

Huijun Di^*, Lei Wang, Guangyou Xu

^*Corresponding author for this work

Tsinghua University

Research output: Contribution to journal › Conference article › peer-review

11 Citations (Scopus)

Abstract

Line detection is one of the most long-lasting problems in image processing. In this paper, we address the problem of detecting strong/weak lines and long/short lines in gray level images simultaneously. Our technique consists of three steps: image gradient enhancement, modified Hough Transform (HT) and line fitting. The gradient direction is fully exploited in our technique, which provides additional cues for weak line detection. Experiments on various images are presented to verify our approach. The results show that our technique has a superior detection rate than conventional HT algorithm, especially for short and weak lines.

Original language	English
Pages (from-to)	835-838
Number of pages	4
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	5286
Issue number	2
DOIs	https://doi.org/10.1117/12.538699
Publication status	Published - 2003
Externally published	Yes
Event	Third International Symposium on Multispectral Image Processing and Pattern Recognition - Beijing, China Duration: 20 Oct 2003 → 22 Oct 2003

Keywords

Canny edge detector
Gradient enhancement
Hough Transform
Line detection

Access to Document

10.1117/12.538699

Cite this

@article{14e410f9b1624f4183ad614f5e53f7eb,

title = "A Three-step Technique of Robust Line Detection with Modified Hough Transform",

abstract = "Line detection is one of the most long-lasting problems in image processing. In this paper, we address the problem of detecting strong/weak lines and long/short lines in gray level images simultaneously. Our technique consists of three steps: image gradient enhancement, modified Hough Transform (HT) and line fitting. The gradient direction is fully exploited in our technique, which provides additional cues for weak line detection. Experiments on various images are presented to verify our approach. The results show that our technique has a superior detection rate than conventional HT algorithm, especially for short and weak lines.",

keywords = "Canny edge detector, Gradient enhancement, Hough Transform, Line detection",

author = "Huijun Di and Lei Wang and Guangyou Xu",

year = "2003",

doi = "10.1117/12.538699",

language = "English",

volume = "5286",

pages = "835--838",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

number = "2",

note = "Third International Symposium on Multispectral Image Processing and Pattern Recognition ; Conference date: 20-10-2003 Through 22-10-2003",

}

TY - JOUR

T1 - A Three-step Technique of Robust Line Detection with Modified Hough Transform

AU - Di, Huijun

AU - Wang, Lei

AU - Xu, Guangyou

PY - 2003

Y1 - 2003

N2 - Line detection is one of the most long-lasting problems in image processing. In this paper, we address the problem of detecting strong/weak lines and long/short lines in gray level images simultaneously. Our technique consists of three steps: image gradient enhancement, modified Hough Transform (HT) and line fitting. The gradient direction is fully exploited in our technique, which provides additional cues for weak line detection. Experiments on various images are presented to verify our approach. The results show that our technique has a superior detection rate than conventional HT algorithm, especially for short and weak lines.

AB - Line detection is one of the most long-lasting problems in image processing. In this paper, we address the problem of detecting strong/weak lines and long/short lines in gray level images simultaneously. Our technique consists of three steps: image gradient enhancement, modified Hough Transform (HT) and line fitting. The gradient direction is fully exploited in our technique, which provides additional cues for weak line detection. Experiments on various images are presented to verify our approach. The results show that our technique has a superior detection rate than conventional HT algorithm, especially for short and weak lines.

KW - Canny edge detector

KW - Gradient enhancement

KW - Hough Transform

KW - Line detection

UR - http://www.scopus.com/inward/record.url?scp=1242353048&partnerID=8YFLogxK

U2 - 10.1117/12.538699

DO - 10.1117/12.538699

M3 - Conference article

AN - SCOPUS:1242353048

SN - 0277-786X

VL - 5286

SP - 835

EP - 838

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

IS - 2

T2 - Third International Symposium on Multispectral Image Processing and Pattern Recognition

Y2 - 20 October 2003 through 22 October 2003

ER -

A Three-step Technique of Robust Line Detection with Modified Hough Transform

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this