Resolution-Independent Superpixels Based on Convex Constrained Meshes Without Small Angles

@inproceedings{Forsythe2016ResolutionIndependentSB,
  title={Resolution-Independent Superpixels Based on Convex Constrained Meshes Without Small Angles},
  author={Jeremy Forsythe and Vitaliy Kurlin and Andrew W. Fitzgibbon},
  booktitle={ISVC},
  year={2016}
}
The over-segmentation problem for images is studied in the 8 new resolution-independent formulation when a large image is approx9 imated by a small number of convex polygons with straight edges at 10 subpixel precision. These polygonal superpixels are obtained by refining 11 and extending subpixel edge segments to a full mesh of convex polygons 12 without small angles and with approximation guarantees. Another nov13 elty is the objective error difference between an original pixel-based image 14… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 15 references

Resolution-independent superpixels based 281 on convex constrained meshes (full version) (2016) http://kurlin.org

J. Forsythe, V. Kurlin, A. Fitzgibbon
2016
View 4 Excerpts
Highly Influenced

Image partitioning into convex polygons

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 6 Excerpts
Highly Influenced

Normalized Cuts and Image Segmentation

View 4 Excerpts
Highly Influenced

Efficient Graph-Based Image Segmentation

International Journal of Computer Vision • 2004
View 3 Excerpts
Highly Influenced

A unifying resolution-independent formulation for early vision

2012 IEEE Conference on Computer Vision and Pattern Recognition • 2012
View 1 Excerpt

SLIC Superpixels Compared to State-of-the-Art Superpixel Methods

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2012
View 2 Excerpts

Contour Detection and Hierarchical Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2011
View 3 Excerpts

Similar Papers

Loading similar papers…