Globally optimal segmentation of multi-region objects

@article{Delong2009GloballyOS,
  title={Globally optimal segmentation of multi-region objects},
  author={Andrew Delong and Yuri Boykov},
  journal={2009 IEEE 12th International Conference on Computer Vision},
  year={2009},
  pages={285-292}
}
  • Andrew Delong, Yuri Boykov
  • Published 1 September 2009
  • Computer Science
  • 2009 IEEE 12th International Conference on Computer Vision
Many objects contain spatially distinct regions, each with a unique colour/texture model. Mixture models ignore the spatial distribution of colours within an object, and thus cannot distinguish between coherent parts versus randomly distributed colours. We show how to encode geometric interactions between distinct region+boundary models, such as regions being interior/exterior to each other along with preferred distances between their boundaries. With a single graph cut, our method extracts… 
Multi-object Graph-based Segmentation with Non-overlapping Surfaces
TLDR
This paper presents an extension to graph cut based methods which can provide a globally optimal segmentation of thousands of objects while guaranteeing no overlap and shows both quantitative and qualitative improvements.
Bounded Labeling Function for Global Segmentation of Multi-part Objects with Geometric Constraints
TLDR
This paper augments the popular Mum ford-Shah model to incorporate two important geometrical constraints, termed containment and detachment, between different regions with a specified minimum distance between their boundaries and shows that the proposed convex continuous method is superior to other state-of-the-art methods, including its discrete counterpart, in terms of memory usage, and metrication errors.
Local Optimization Based Segmentation of Spatially-Recurring, Multi-Region Objects With Part Configuration Constraints
TLDR
This paper augments the level set framework with the ability to handle these two intuitive geometric relationships, containment and exclusion, along with a distance constraint between boundaries of multi-region objects, and compared this framework with its counterpart methods in the discrete domain.
A Continuous Max-Flow Approach to General Hierarchical Multi-Labelling Problems
TLDR
Generalized Hierarchical Max-Flow (GHMF) segmentation is presented, which captures simple anatomical part-whole relationships in the form of an unconstrained hierarchy, allowing for spatial grouping and clustering of labels in a globally optimal convex optimization framework.
Hausdorff Distance Constraint for Multi-surface Segmentation
TLDR
This work develops a submodular-supermodular procedure that converges to a locally optimal solution well-approximating the problem and gets useful solutions for many challenging medical applications including MRI and ultrasound images.
Efficient Interactive Multi-object Segmentation in Medical Images
TLDR
An efficient method is proposed for the multiple object segmentation of medical images by constructing an associated weighted digraph of superpixels, attending its individual high-level priors and considering structural relations of inclusion and exclusion.
Interactive Segmentation with Super-Labels
TLDR
This work proposes a novel segmentation energy that can model complex appearance by representing the appearance of each object by a set of distinct spatially coherent models and introduces the hierarchical Potts (hPotts) prior to govern spatial coherence within each level.
Optimal Multi-Object Segmentation with Novel Gradient Vector Flow Based Shape Priors
Surface-Region Context in Optimal Multi-object Graph-Based Segmentation: Robust Delineation of Pulmonary Tumors
TLDR
A novel solution to a segmentation problem, in which target objects of arbitrary shape mutually interact with terrain-like surfaces, which widely exists in the medical imaging field, is reported.
Region growing using superpixels with learned shape prior
TLDR
The performance of the proposed method is demonstrated and it is compared with alternative approaches on the task of segmenting individual eggs in microscopy images of Drosophila ovaries on the level of superpixels instead of pixels.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 31 REFERENCES
Shape prior segmentation of multiple objects with graph cuts
  • N. Vu, B. S. Manjunath
  • Computer Science
    2008 IEEE Conference on Computer Vision and Pattern Recognition
  • 2008
TLDR
A major advantage of this approach is that the segmentation energy is minimized directly without having to compute its gradient, which can be a cumbersome task and often relies on approximations.
Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images
TLDR
A new technique for general purpose interactive segmentation of N-dimensional images where the user marks certain pixels as “object” or “background” to provide hard constraints for segmentation.
Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach
TLDR
An optimal surface detection method capable of simultaneously detecting multiple interacting surfaces, in which the optimality is controlled by the cost functions designed for individual surfaces and by several geometric constraints defining the surface smoothness and interrelations is developed.
Interactive graph cut based segmentation with shape priors
  • D. Freedman, Tao Zhang
  • Computer Science
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
TLDR
This work devise a graph cut algorithm for interactive segmentation which incorporates shape priors, and positive results on both medical and natural images are demonstrated.
Graph cut based image segmentation with connectivity priors
TLDR
This work forms several versions of the connectivity constraint and shows that the corresponding optimization problems are all NP-hard.
"GrabCut": interactive foreground extraction using iterated graph cuts
TLDR
A more powerful, iterative version of the optimisation of the graph-cut approach is developed and the power of the iterative algorithm is used to simplify substantially the user interaction needed for a given quality of result.
Star Shape Prior for Graph-Cut Image Segmentation
TLDR
This paper shows how to implement a star shape prior into graph cut segmentation, a generic shape prior that applies to a wide class of objects, in particular to convex objects, and shows that in many cases, it can achieve an accurate object segmentation with only a single pixel, the center of the object, provided by the user, which is rarely possible with standard graph cut interactive segmentation.
Fast Approximate Energy Minimization via Graph Cuts
TLDR
This work presents two algorithms based on graph cuts that efficiently find a local minimum with respect to two types of large moves, namely expansion moves and swap moves that allow important cases of discontinuity preserving energies.
Recovering Surface Layout from an Image
TLDR
This paper takes the first step towards constructing the surface layout, a labeling of the image intogeometric classes, to learn appearance-based models of these geometric classes, which coarsely describe the 3D scene orientation of each image region.
Multilabel random walker image segmentation using prior models
  • L. Grady
  • Computer Science
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
TLDR
It is shown that incorporation of a nonparametric probability density model allows for an extended random walkers algorithm that can locate disconnected objects and does not require user-specified labels.
...
1
2
3
4
...