Continuous Multiclass Labeling Approaches and Algorithms

Details Continuous Multiclass Labeling Approaches and Algorithms Continuous Multiclass Labeling Approaches and Algorithms

2011-02-26

arxiv.org/abs/1102.5448v2

Computer Science

Computer Vision and Pattern Recognition

Scientific paper

We study convex relaxations of the image labeling problem on a continuous domain with regularizers based on metric interaction potentials. The generic framework ensures existence of minimizers and covers a wide range of relaxations of the originally combinatorial problem. We focus on two specific relaxations that differ in flexibility and simplicity -- one can be used to tightly relax any metric interaction potential, while the other one only covers Euclidean metrics but requires less computational effort. For solving the nonsmooth discretized problem, we propose a globally convergent Douglas-Rachford scheme, and show that a sequence of dual iterates can be recovered in order to provide a posteriori optimality bounds. In a quantitative comparison to two other first-order methods, the approach shows competitive performance on synthetical and real-world images. By combining the method with an improved binarization technique for nonstandard potentials, we were able to routinely recover discrete solutions within 1%--5% of the global optimum for the combinatorial image labeling problem.

Affiliated with

Also associated with

No associations

Rating

Continuous Multiclass Labeling Approaches and Algorithms does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Continuous Multiclass Labeling Approaches and Algorithms, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Continuous Multiclass Labeling Approaches and Algorithms will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-53665