Improved force field for vector field convolution method

Andrea Kovacs, T. Szirányi

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

6 Citations (Scopus)

Abstract

Parametric active contours are efficient tools for boundary detection. However, existing external-energy-inspired methods have difficulties when detecting high curvature, noisy or low contrasted contours and they often suffer from initialization sensitivity. To address these issues, this paper introduces Harris-based Vector Field Convolution (HVFC), operating with the modified characteristic function of Harris corner detector used in the feature map of the external force component. Initial contour is calculated as the convex hull of the most salient points of the map. Experimental results show that HVFC outperforms other state-of-the-art methods, when tested on high curvature, noisy or low-contrasted contours.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages2853-2856
Number of pages4
DOIs
Publication statusPublished - 2011
Event2011 18th IEEE International Conference on Image Processing, ICIP 2011 - Brussels, Belgium
Duration: Sep 11 2011Sep 14 2011

Other

Other2011 18th IEEE International Conference on Image Processing, ICIP 2011
CountryBelgium
CityBrussels
Period9/11/119/14/11

Fingerprint

Convolution
Detectors

Keywords

  • Boundary analysis
  • Harris characteristic function
  • vector field convolution

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Kovacs, A., & Szirányi, T. (2011). Improved force field for vector field convolution method. In Proceedings - International Conference on Image Processing, ICIP (pp. 2853-2856). [6116142] https://doi.org/10.1109/ICIP.2011.6116142

Improved force field for vector field convolution method. / Kovacs, Andrea; Szirányi, T.

Proceedings - International Conference on Image Processing, ICIP. 2011. p. 2853-2856 6116142.

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

Kovacs, A & Szirányi, T 2011, Improved force field for vector field convolution method. in Proceedings - International Conference on Image Processing, ICIP., 6116142, pp. 2853-2856, 2011 18th IEEE International Conference on Image Processing, ICIP 2011, Brussels, Belgium, 9/11/11. https://doi.org/10.1109/ICIP.2011.6116142
Kovacs A, Szirányi T. Improved force field for vector field convolution method. In Proceedings - International Conference on Image Processing, ICIP. 2011. p. 2853-2856. 6116142 https://doi.org/10.1109/ICIP.2011.6116142
Kovacs, Andrea ; Szirányi, T. / Improved force field for vector field convolution method. Proceedings - International Conference on Image Processing, ICIP. 2011. pp. 2853-2856
@inproceedings{3d318b35d220421795717cee0ac8173f,
title = "Improved force field for vector field convolution method",
abstract = "Parametric active contours are efficient tools for boundary detection. However, existing external-energy-inspired methods have difficulties when detecting high curvature, noisy or low contrasted contours and they often suffer from initialization sensitivity. To address these issues, this paper introduces Harris-based Vector Field Convolution (HVFC), operating with the modified characteristic function of Harris corner detector used in the feature map of the external force component. Initial contour is calculated as the convex hull of the most salient points of the map. Experimental results show that HVFC outperforms other state-of-the-art methods, when tested on high curvature, noisy or low-contrasted contours.",
keywords = "Boundary analysis, Harris characteristic function, vector field convolution",
author = "Andrea Kovacs and T. Szir{\'a}nyi",
year = "2011",
doi = "10.1109/ICIP.2011.6116142",
language = "English",
isbn = "9781457713033",
pages = "2853--2856",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Improved force field for vector field convolution method

AU - Kovacs, Andrea

AU - Szirányi, T.

PY - 2011

Y1 - 2011

N2 - Parametric active contours are efficient tools for boundary detection. However, existing external-energy-inspired methods have difficulties when detecting high curvature, noisy or low contrasted contours and they often suffer from initialization sensitivity. To address these issues, this paper introduces Harris-based Vector Field Convolution (HVFC), operating with the modified characteristic function of Harris corner detector used in the feature map of the external force component. Initial contour is calculated as the convex hull of the most salient points of the map. Experimental results show that HVFC outperforms other state-of-the-art methods, when tested on high curvature, noisy or low-contrasted contours.

AB - Parametric active contours are efficient tools for boundary detection. However, existing external-energy-inspired methods have difficulties when detecting high curvature, noisy or low contrasted contours and they often suffer from initialization sensitivity. To address these issues, this paper introduces Harris-based Vector Field Convolution (HVFC), operating with the modified characteristic function of Harris corner detector used in the feature map of the external force component. Initial contour is calculated as the convex hull of the most salient points of the map. Experimental results show that HVFC outperforms other state-of-the-art methods, when tested on high curvature, noisy or low-contrasted contours.

KW - Boundary analysis

KW - Harris characteristic function

KW - vector field convolution

UR - http://www.scopus.com/inward/record.url?scp=84856271935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856271935&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2011.6116142

DO - 10.1109/ICIP.2011.6116142

M3 - Conference contribution

SN - 9781457713033

SP - 2853

EP - 2856

BT - Proceedings - International Conference on Image Processing, ICIP

ER -