Contour-based shape representation using principal curves

Esra Ataer-Cansizoglu, Erhan Bas, Jayashree Kalpathy-Cramer, Greg C. Sharp, Deniz Erdogmus

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Extraction and representation of contours are challenging problems and are crucial for many image processing applications. In this study, given a membership function that returns the score of a point belonging to a contour, we propose a method for contour representation based on the principal curve (PC) of this function. The proposed method provides a piecewise linear representation of the contour with fewer points while preserving shape. Varied experiments are conducted, including lung boundary representation in CT images and shape representation in handwritten images. The results show that the technique provides accurate shape representation.

Original languageEnglish (US)
Pages (from-to)1140-1150
Number of pages11
JournalPattern Recognition
Volume46
Issue number4
DOIs
StatePublished - Apr 2013
Externally publishedYes

Fingerprint

Membership functions
Image processing
Experiments

Keywords

  • Curve/contour matching
  • Shape representation and analysis

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Ataer-Cansizoglu, E., Bas, E., Kalpathy-Cramer, J., Sharp, G. C., & Erdogmus, D. (2013). Contour-based shape representation using principal curves. Pattern Recognition, 46(4), 1140-1150. https://doi.org/10.1016/j.patcog.2012.10.014

Contour-based shape representation using principal curves. / Ataer-Cansizoglu, Esra; Bas, Erhan; Kalpathy-Cramer, Jayashree; Sharp, Greg C.; Erdogmus, Deniz.

In: Pattern Recognition, Vol. 46, No. 4, 04.2013, p. 1140-1150.

Research output: Contribution to journalArticle

Ataer-Cansizoglu, E, Bas, E, Kalpathy-Cramer, J, Sharp, GC & Erdogmus, D 2013, 'Contour-based shape representation using principal curves', Pattern Recognition, vol. 46, no. 4, pp. 1140-1150. https://doi.org/10.1016/j.patcog.2012.10.014
Ataer-Cansizoglu E, Bas E, Kalpathy-Cramer J, Sharp GC, Erdogmus D. Contour-based shape representation using principal curves. Pattern Recognition. 2013 Apr;46(4):1140-1150. https://doi.org/10.1016/j.patcog.2012.10.014
Ataer-Cansizoglu, Esra ; Bas, Erhan ; Kalpathy-Cramer, Jayashree ; Sharp, Greg C. ; Erdogmus, Deniz. / Contour-based shape representation using principal curves. In: Pattern Recognition. 2013 ; Vol. 46, No. 4. pp. 1140-1150.
@article{6fb0fc597e9d40ca909aab7a84a3909e,
title = "Contour-based shape representation using principal curves",
abstract = "Extraction and representation of contours are challenging problems and are crucial for many image processing applications. In this study, given a membership function that returns the score of a point belonging to a contour, we propose a method for contour representation based on the principal curve (PC) of this function. The proposed method provides a piecewise linear representation of the contour with fewer points while preserving shape. Varied experiments are conducted, including lung boundary representation in CT images and shape representation in handwritten images. The results show that the technique provides accurate shape representation.",
keywords = "Curve/contour matching, Shape representation and analysis",
author = "Esra Ataer-Cansizoglu and Erhan Bas and Jayashree Kalpathy-Cramer and Sharp, {Greg C.} and Deniz Erdogmus",
year = "2013",
month = "4",
doi = "10.1016/j.patcog.2012.10.014",
language = "English (US)",
volume = "46",
pages = "1140--1150",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - Contour-based shape representation using principal curves

AU - Ataer-Cansizoglu, Esra

AU - Bas, Erhan

AU - Kalpathy-Cramer, Jayashree

AU - Sharp, Greg C.

AU - Erdogmus, Deniz

PY - 2013/4

Y1 - 2013/4

N2 - Extraction and representation of contours are challenging problems and are crucial for many image processing applications. In this study, given a membership function that returns the score of a point belonging to a contour, we propose a method for contour representation based on the principal curve (PC) of this function. The proposed method provides a piecewise linear representation of the contour with fewer points while preserving shape. Varied experiments are conducted, including lung boundary representation in CT images and shape representation in handwritten images. The results show that the technique provides accurate shape representation.

AB - Extraction and representation of contours are challenging problems and are crucial for many image processing applications. In this study, given a membership function that returns the score of a point belonging to a contour, we propose a method for contour representation based on the principal curve (PC) of this function. The proposed method provides a piecewise linear representation of the contour with fewer points while preserving shape. Varied experiments are conducted, including lung boundary representation in CT images and shape representation in handwritten images. The results show that the technique provides accurate shape representation.

KW - Curve/contour matching

KW - Shape representation and analysis

UR - http://www.scopus.com/inward/record.url?scp=84871270448&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871270448&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2012.10.014

DO - 10.1016/j.patcog.2012.10.014

M3 - Article

VL - 46

SP - 1140

EP - 1150

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 4

ER -