A Novel Linelet-Based Representation for Line Segment Detection

Nam Gyu Cho; Alan Yuille; Seong Whan Lee

doi:10.1109/TPAMI.2017.2703841

A Novel Linelet-Based Representation for Line Segment Detection

Nam Gyu Cho, Alan Yuille, Seong Whan Lee

Department of Brain and Cognitive Engineering

Research output: Contribution to journal › Article › peer-review

21 Citations (Scopus)

Abstract

This paper proposes a method for line segment detection in digital images. We propose a novel linelet-based representation to model intrinsic properties of line segments in rasterized image space. Based on this, line segment detection, validation, and aggregation frameworks are constructed. For a numerical evaluation on real images, we propose a new benchmark dataset of real images with annotated lines called YorkUrban-LineSegment. The results show that the proposed method outperforms state-of-the-art methods numerically and visually. To our best knowledge, this is the first report of numerical evaluation of line segment detection on real images.

Original language	English
Pages (from-to)	1195-1208
Number of pages	14
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	40
Issue number	5
DOIs	https://doi.org/10.1109/TPAMI.2017.2703841
Publication status	Published - 2018 May 1

Keywords

Intrinsic properties of digital line
image edge detection
line segment validation
probabilistic line segment representation

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics

Access to Document

10.1109/TPAMI.2017.2703841

Fingerprint Dive into the research topics of 'A Novel Linelet-Based Representation for Line Segment Detection'. Together they form a unique fingerprint.

Cite this

@article{4491bf20f9844600b88e65e45edabb08,

title = "A Novel Linelet-Based Representation for Line Segment Detection",

abstract = "This paper proposes a method for line segment detection in digital images. We propose a novel linelet-based representation to model intrinsic properties of line segments in rasterized image space. Based on this, line segment detection, validation, and aggregation frameworks are constructed. For a numerical evaluation on real images, we propose a new benchmark dataset of real images with annotated lines called YorkUrban-LineSegment. The results show that the proposed method outperforms state-of-the-art methods numerically and visually. To our best knowledge, this is the first report of numerical evaluation of line segment detection on real images.",

keywords = "Intrinsic properties of digital line, image edge detection, line segment validation, probabilistic line segment representation",

author = "Cho, {Nam Gyu} and Alan Yuille and Lee, {Seong Whan}",

year = "2018",

month = may,

day = "1",

doi = "10.1109/TPAMI.2017.2703841",

language = "English",

volume = "40",

pages = "1195--1208",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "5",

}

TY - JOUR

T1 - A Novel Linelet-Based Representation for Line Segment Detection

AU - Cho, Nam Gyu

AU - Yuille, Alan

AU - Lee, Seong Whan

PY - 2018/5/1

Y1 - 2018/5/1

N2 - This paper proposes a method for line segment detection in digital images. We propose a novel linelet-based representation to model intrinsic properties of line segments in rasterized image space. Based on this, line segment detection, validation, and aggregation frameworks are constructed. For a numerical evaluation on real images, we propose a new benchmark dataset of real images with annotated lines called YorkUrban-LineSegment. The results show that the proposed method outperforms state-of-the-art methods numerically and visually. To our best knowledge, this is the first report of numerical evaluation of line segment detection on real images.

AB - This paper proposes a method for line segment detection in digital images. We propose a novel linelet-based representation to model intrinsic properties of line segments in rasterized image space. Based on this, line segment detection, validation, and aggregation frameworks are constructed. For a numerical evaluation on real images, we propose a new benchmark dataset of real images with annotated lines called YorkUrban-LineSegment. The results show that the proposed method outperforms state-of-the-art methods numerically and visually. To our best knowledge, this is the first report of numerical evaluation of line segment detection on real images.

KW - Intrinsic properties of digital line

KW - image edge detection

KW - line segment validation

KW - probabilistic line segment representation

UR - http://www.scopus.com/inward/record.url?scp=85044856825&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044856825&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2017.2703841

DO - 10.1109/TPAMI.2017.2703841

M3 - Article

C2 - 28504933

AN - SCOPUS:85044856825

VL - 40

SP - 1195

EP - 1208

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 5

ER -