Advanced search
1 file | 2.56 MB

A fast one-pixel wide contour detection method for shapes contour traversal in binary images

Author
Organization
Abstract
Contour detection is an important step in contour based object analysis in 2D images. We present a novel method for contour detection optimized for contour traversal tasks in 2D images. The method is based on morphological operations and detects a one-pixel wide contour around objects in binary images. Performance of the method is evaluated on ground truth images from our dataset created by manually tracing the contour in images. Proposed method achieves high DICE coefficient overlap to ground truth images and superior detection compared to other state-of-the-art methods.
Keywords
Contour tracing, contour detection, binary image

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 2.56 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Leventić, Hrvoje, Tomislav Keser, and Krešimir Vdovjak. 2018. “A Fast One-pixel Wide Contour Detection Method for Shapes Contour Traversal in Binary Images.” In Proceedings of International Conference on Smart Systems and Technologies 2018, ed. Drago Žagar, Goran Martinović, Snježana Rimac Drlje, and Irena Galić, 11–14. Osijek: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek.
APA
Leventić, H., Keser, T., & Vdovjak, K. (2018). A fast one-pixel wide contour detection method for shapes contour traversal in binary images. In D. Žagar, G. Martinović, S. Rimac Drlje, & I. Galić (Eds.), Proceedings of International Conference on Smart Systems and Technologies 2018 (pp. 11–14). Presented at the International Conference on Smart Systems and Technologies 2018, Osijek: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek.
Vancouver
1.
Leventić H, Keser T, Vdovjak K. A fast one-pixel wide contour detection method for shapes contour traversal in binary images. In: Žagar D, Martinović G, Rimac Drlje S, Galić I, editors. Proceedings of International Conference on Smart Systems and Technologies 2018. Osijek: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2018. p. 11–4.
MLA
Leventić, Hrvoje, Tomislav Keser, and Krešimir Vdovjak. “A Fast One-pixel Wide Contour Detection Method for Shapes Contour Traversal in Binary Images.” Proceedings of International Conference on Smart Systems and Technologies 2018. Ed. Drago Žagar et al. Osijek: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. 11–14. Print.
@inproceedings{8583480,
  abstract     = {Contour detection is an important step in contour
based object analysis in 2D images. We present a novel method
for contour detection optimized for contour traversal tasks in 2D
images. The method is based on morphological operations and
detects a one-pixel wide contour around objects in binary images.
Performance of the method is evaluated on ground truth images
from our dataset created by manually tracing the contour in
images. Proposed method achieves high DICE coefficient overlap
to ground truth images and superior detection compared to other
state-of-the-art methods.
},
  author       = {Leventi\'{c}, Hrvoje and Keser, Tomislav and Vdovjak, Kre\v{s}imir},
  booktitle    = {Proceedings of International Conference on Smart Systems and Technologies 2018},
  editor       = {\v{Z}agar, Drago and Martinovi\'{c}, Goran and Rimac Drlje, Snje\v{z}ana  and Gali\'{c}, Irena },
  isbn         = {978-1-5386-7189-4},
  language     = {eng},
  location     = {Osijek, Croatia},
  pages        = {11--14},
  publisher    = { Faculty of Electrical Engineering, Computer Science and Information Technology Osijek},
  title        = {A fast one-pixel wide contour detection method for shapes contour traversal in binary images},
  year         = {2018},
}