An Approach Towards Fast Gradient-based Image Segmentation

Abstract—In this paper we present and investigate an approach
to fast multi-label color image segmentation using convex
optimization techniques. The presented model is in some ways
related to the well-known Mumford-Shah model, but deviates in
certain important aspects. The optimization problem has been
designed with two goals in mind: The objective function should
represent fundamental concepts of image segmentation, such as
incorporation of weighted curve length and variation of intensity
in the segmented regions, while allowing transformation into a
convex concave saddle point problem that is computationally
inexpensive to solve. This paper introduces such a model, the
nontrivial transformation of this model into a convex-concave
saddle point problem, and the numerical treatment of the
problem. We evaluate our approach by applying our algorithm
to various images and show that our results are competitive in
terms of quality at unprecedentedly low computation times. Our
algorithm allows high-quality segmentation of megapixel images
in a few seconds and achieves interactive performance for low
resolution images.
Author(s): | Benjamin Hell, Marc Kassubeck, Pablo Bauszat, Martin Eisemann, Marcus Magnor |
---|---|
Published: | September 2015 |
Type: | Article |
Journal: | IEEE Transactions on Image Processing (TIP) Vol. 24 |
Project(s): | Reality CG |
@article{hell2015fastgradientbasedimagessegmentation, title = {An Approach Towards Fast Gradient-based Image Segmentation}, author = {Hell, Benjamin and Kassubeck, Marc and Bauszat, Pablo and Eisemann, Martin and Magnor, Marcus}, journal = {{IEEE} Transactions on Image Processing ({TIP})}, volume = {24}, number = {9}, pages = {2633--2645}, month = {Sep}, year = {2015} }
Authors
Benjamin Hell
Fmr. ResearcherMarc Kassubeck
Fmr. ResearcherPablo Bauszat
Fmr. ResearcherMartin Eisemann
DirectorMarcus Magnor
Director, Chair