Advanced search
1 file | 8.11 MB Add to list

Superpixel segmentation based on anisotropic edge strength

Author
Organization
Abstract
Superpixel segmentation can benefit from the use of an appropriate method to measure edge strength. In this paper, we present such a method based on the first derivative of anisotropic Gaussian kernels. The kernels can capture the position, direction, prominence, and scale of the edge to be detected. We incorporate the anisotropic edge strength into the distance measure between neighboring superpixels, thereby improving the performance of an existing graph-based superpixel segmentation method. Experimental results validate the superiority of our method in generating superpixels over the competing methods. It is also illustrated that the proposed superpixel segmentation method can facilitate subsequent saliency detection.
Keywords
edge strength, first derivative of anisotropic Gaussian kernel, superpixel segmentation, distance measure, graph-based method, CONTOUR-DETECTION, NOISE

Downloads

  • KERMIT-A1-521.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 8.11 MB

Citation

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

MLA
WANG, Gang, and Bernard De Baets. “Superpixel Segmentation Based on Anisotropic Edge Strength.” JOURNAL OF IMAGING, vol. 5, no. 6, 2019, doi:10.3390/jimaging5060057.
APA
WANG, G., & De Baets, B. (2019). Superpixel segmentation based on anisotropic edge strength. JOURNAL OF IMAGING, 5(6). https://doi.org/10.3390/jimaging5060057
Chicago author-date
WANG, Gang, and Bernard De Baets. 2019. “Superpixel Segmentation Based on Anisotropic Edge Strength.” JOURNAL OF IMAGING 5 (6). https://doi.org/10.3390/jimaging5060057.
Chicago author-date (all authors)
WANG, Gang, and Bernard De Baets. 2019. “Superpixel Segmentation Based on Anisotropic Edge Strength.” JOURNAL OF IMAGING 5 (6). doi:10.3390/jimaging5060057.
Vancouver
1.
WANG G, De Baets B. Superpixel segmentation based on anisotropic edge strength. JOURNAL OF IMAGING. 2019;5(6).
IEEE
[1]
G. WANG and B. De Baets, “Superpixel segmentation based on anisotropic edge strength,” JOURNAL OF IMAGING, vol. 5, no. 6, 2019.
@article{8626844,
  abstract     = {{Superpixel segmentation can benefit from the use of an appropriate method to measure edge strength. In this paper, we present such a method based on the first derivative of anisotropic Gaussian kernels. The kernels can capture the position, direction, prominence, and scale of the edge to be detected. We incorporate the anisotropic edge strength into the distance measure between neighboring superpixels, thereby improving the performance of an existing graph-based superpixel segmentation method. Experimental results validate the superiority of our method in generating superpixels over the competing methods. It is also illustrated that the proposed superpixel segmentation method can facilitate subsequent saliency detection.}},
  articleno    = {{57}},
  author       = {{WANG, Gang and De Baets, Bernard}},
  issn         = {{2313-433X}},
  journal      = {{JOURNAL OF IMAGING}},
  keywords     = {{edge strength,first derivative of anisotropic Gaussian kernel,superpixel segmentation,distance measure,graph-based method,CONTOUR-DETECTION,NOISE}},
  language     = {{eng}},
  number       = {{6}},
  pages        = {{24}},
  title        = {{Superpixel segmentation based on anisotropic edge strength}},
  url          = {{http://doi.org/10.3390/jimaging5060057}},
  volume       = {{5}},
  year         = {{2019}},
}

Altmetric
View in Altmetric