[Back]


Talks and Poster Presentations (with Proceedings-Entry):

J. Forsythe et al.:
"Resolution-independent superpixels based on convex constrained meshes without small angles";
Talk: International Symposium on Visual Computing, Las Vegas, Nevada, USA; 2016-12-12 - 2016-12-14; in: "Proceedings of ISVC", Lecture Notes in Computer Science (LNCS), Advances in Visual Computing (2016), ISSN: 0302-9743; 223 - 233.



English abstract:
The over-segmentation problem for images is studied in the new resolution-independent formulation when a large image is approximated by a small number of convex polygons with straight edges at subpixel precision. These polygonal superpixels are obtained by refining and extending subpixel edge segments to a full mesh of convex polygons without small angles and with approximation guarantees. Another novelty is the objective error difference between an original pixel-based image and the reconstructed image with a best constant color over each superpixel, which does not need human segmentations. The experiments on images from the Berkeley Segmentation Database show that new meshes are smaller and provide better approximations than the state-of-the-art.


"Official" electronic version of the publication (accessed through its Digital Object Identifier - DOI)
http://dx.doi.org/10.1007/978-3-319-50835-1_21

Electronic version of the publication:
http://publik.tuwien.ac.at/files/publik_253409.pdf


Created from the Publication Database of the Vienna University of Technology.