Robust interactive multi-label segmentation with an advanced edge detector

S. Müller, Peter Ochs, J. Weickert, N. Graf
German Conference on Pattern Recognition (GCPR), Springer, LNCS, Vol.9796: 117--128, 2016
Abstract: Recent advances on convex relaxation methods allow for a flexible formulation of many interactive multi-label segmentation methods. The building blocks are a likelihood specified for each pixel and each label, and a penalty for the boundary length of each segment. While many sophisticated likelihood estimations based on various statistical measures have been investigated, the boundary length is usually measured in a metric induced by simple image gradients. We show that complementing these methods with recent advances of edge detectors yields an immense quality improvement. A remarkable feature of the proposed method is the ability to correct some erroneous labels, when computer generated initial labels are considered. This allows us to improve state-of-the-art methods for motion segmentation in videos by 5-10% with respect to the F-measure (Dice score).
Publisher's link

Other associated files : mueller-gcpr2016.pdf [3.1MB]  

Images and movies


BibTex reference

  author       = "S. M{\"u}ller and P. Ochs and J. Weickert and N. Graf",
  title        = "Robust interactive multi-label segmentation with an advanced edge detector",
  booktitle    = "German Conference on Pattern Recognition (GCPR)",
  series       = "Lecture Notes in Computer Science",
  volume       = "9796",
  pages        = "117--128",
  month        = " ",
  year         = "2016",
  editor       = "B. Andres, B. Rosenhahn",
  publisher    = "Springer",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2016/Och16a"

Other publications in the database