Paper Info
Title
An Adaptive Subdivision Scheme For Quadratic Programming In Multi-Label Image Segmentation
Abstract
We address the problem of efficient, globally optimal multi-label image segmentation. Transforming the discrete labeling problem into a [0, 1]-relaxed binary quadratic program we are able to solve arbitrary convex quadratic labeling tasks in polynomial time. Although this guarantees efficiency in a theoretical sense, large-scale quadratic programs that arise from relaxation can rarely be used for image segmentation directly. We treat this issue by an adaptive domain subdivision scheme, reducing the problem to a short sequence of spatially smoothed medium-scale programs, which subsequently better approximate the large-scale program. Our scheme is globally optimal in terms of the approximated problem. It allows for near-interactive multi-label segmentation and is highly accurate even in the presence of strong noise.
Year
DOI
Venue
2013
10.5244/C.27.109
PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2013
Field
DocType
Citations 
Computer vision,Mathematical optimization,Scale-space segmentation,Computer science,Quadratic equation,Segmentation-based object categorization,Image segmentation,Subdivision,Artificial intelligence,Quadratic programming,Time complexity,Piecewise
Conference
0
PageRank 
References 
Authors
0.34
6
3
Name
Order
Citations
PageRank
Marko Rak1318.37
Tim König212.39
Klaus D. Tönnies321544.39