Active Contours that Grow and Compete Driven by Local Region Descriptors

Cristina Darolti; Erhardt Barth; Christoph Bodensteiner; Ulrich G. Hofmann

doi:10.1117/12.805983

Active Contours that Grow and Compete Driven by Local Region Descriptors

Cristina Darolti, Erhardt Barth, Christoph Bodensteiner, Ulrich G. Hofmann

Abstract

Region-based active contours are a variational framework for image segmentation. It involves estimating the probability distributions of observed features within each image region. Subsequently, these so-called region descriptors are used to generate forces to move the contour toward real image boundaries. In this paper region descriptors are computed from samples within windows centered on contour pixels and they are named local region descriptors (LRDs). With these descriptors we introduce an equation for contour motion with two terms: growing and competing. This equation yields a novel type of AC that can adjust the behavior of contour pieces to image patches and to the presence of other contours. The quality of the proposed motion model is demonstrated on complex images.

Original language	English
Title of host publication	Image Processing: Algorithms and Systems VII
Number of pages	9
Volume	7245
Publisher	SPIE
Publication date	15.06.2009
Article number	72450F
ISBN (Print)	978-081947495-7
DOIs	https://doi.org/10.1117/12.805983
Publication status	Published - 15.06.2009
Event	Image Processing: Algorithms and Systems VII - San Jose, United States Duration: 19.01.2009 → 22.01.2009 Conference number: 76102

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1117/12.805983

Cite this

@inproceedings{b6564601d6d24d31a021c4f411b8719c,

title = "Active Contours that Grow and Compete Driven by Local Region Descriptors",

abstract = "Region-based active contours are a variational framework for image segmentation. It involves estimating the probability distributions of observed features within each image region. Subsequently, these so-called region descriptors are used to generate forces to move the contour toward real image boundaries. In this paper region descriptors are computed from samples within windows centered on contour pixels and they are named local region descriptors (LRDs). With these descriptors we introduce an equation for contour motion with two terms: growing and competing. This equation yields a novel type of AC that can adjust the behavior of contour pieces to image patches and to the presence of other contours. The quality of the proposed motion model is demonstrated on complex images.",

author = "Cristina Darolti and Erhardt Barth and Christoph Bodensteiner and Hofmann, {Ulrich G.}",

year = "2009",

month = jun,

day = "15",

doi = "10.1117/12.805983",

language = "English",

isbn = "978-081947495-7",

volume = "7245",

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

publisher = "SPIE",

booktitle = "Image Processing: Algorithms and Systems VII",

note = "Image Processing: Algorithms and Systems VII ; Conference date: 19-01-2009 Through 22-01-2009",

}

Darolti, C, Barth, E, Bodensteiner, C & Hofmann, UG 2009, Active Contours that Grow and Compete Driven by Local Region Descriptors. in Image Processing: Algorithms and Systems VII. vol. 7245, 72450F, Proceedings of SPIE - The International Society for Optical Engineering, vol. 7245, SPIE, Image Processing: Algorithms and Systems VII, San Jose, California, United States, 19.01.09. https://doi.org/10.1117/12.805983

Active Contours that Grow and Compete Driven by Local Region Descriptors. / Darolti, Cristina; Barth, Erhardt; Bodensteiner, Christoph et al.
Image Processing: Algorithms and Systems VII. Vol. 7245 SPIE, 2009. 72450F (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7245).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Active Contours that Grow and Compete Driven by Local Region Descriptors

AU - Darolti, Cristina

AU - Barth, Erhardt

AU - Bodensteiner, Christoph

AU - Hofmann, Ulrich G.

N1 - Conference code: 76102

PY - 2009/6/15

Y1 - 2009/6/15

N2 - Region-based active contours are a variational framework for image segmentation. It involves estimating the probability distributions of observed features within each image region. Subsequently, these so-called region descriptors are used to generate forces to move the contour toward real image boundaries. In this paper region descriptors are computed from samples within windows centered on contour pixels and they are named local region descriptors (LRDs). With these descriptors we introduce an equation for contour motion with two terms: growing and competing. This equation yields a novel type of AC that can adjust the behavior of contour pieces to image patches and to the presence of other contours. The quality of the proposed motion model is demonstrated on complex images.

AB - Region-based active contours are a variational framework for image segmentation. It involves estimating the probability distributions of observed features within each image region. Subsequently, these so-called region descriptors are used to generate forces to move the contour toward real image boundaries. In this paper region descriptors are computed from samples within windows centered on contour pixels and they are named local region descriptors (LRDs). With these descriptors we introduce an equation for contour motion with two terms: growing and competing. This equation yields a novel type of AC that can adjust the behavior of contour pieces to image patches and to the presence of other contours. The quality of the proposed motion model is demonstrated on complex images.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-66749147696&origin=inward&txGid=bb15ae1cbb640dee40477dc9ed174d55

U2 - 10.1117/12.805983

DO - 10.1117/12.805983

M3 - Conference contribution

SN - 978-081947495-7

VL - 7245

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Image Processing: Algorithms and Systems VII

PB - SPIE

T2 - Image Processing: Algorithms and Systems VII

Y2 - 19 January 2009 through 22 January 2009

ER -

Active Contours that Grow and Compete Driven by Local Region Descriptors

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this