A Mutual Reference Shape for Segmentation Fusion and Evaluation

@inproceedings{JehanBesson2021AMR,
  title={A Mutual Reference Shape for Segmentation Fusion and Evaluation},
  author={S. Jehan-Besson and R{\'e}gis Clouard and Christophe Tilmant and Alain De Cesare and Alain Lalande and Jessica Lebenberg and Patrick Clarysse and Laurent Sarry and Fr{\'e}d{\'e}rique Frouin and Mireille Garreau},
  year={2021}
}
This paper proposes the estimation of a mutual shape from a set of different segmentation results using both active contours and information theory. The mutual shape is here defined as a consensus shape estimated from a set of different segmentations of the same object. In an original manner, such a shape is defined as the minimum of a criterion that benefits from both the mutual information and the joint entropy of the input segmentations. This energy criterion is justified using similarities… Expand

References

SHOWING 1-10 OF 47 REFERENCES
A mutual reference shape based on information theory
TLDR
This paper considers the estimation of a reference shape from a set of different segmentation results using both active contours and information theory to solve the shape optimization problem of cardiac segmentation methods in MRI. Expand
Segmentation of Vectorial Image Features Using Shape Gradients and Information Measures
TLDR
This paper chooses to evaluate, within each region to be segmented, the average quantity of information carried out by the vectorial features, namely the joint entropy of vector components, and evaluates the entropy using non parametric probability density functions. Expand
Nonparametric methods for image segmentation using information theory and curve evolution
TLDR
This work casts the segmentation problem as the maximization of the mutual information between the region labels and the image pixel intensities, subject to a constraint on the total length of the region boundaries, and forms the problem based on nonparametric density estimates. Expand
Image Segmentation Using Active Contours: Calculus of Variations or Shape Gradients?
TLDR
This work considers the problem of segmenting an image through the minimization of an energy criterion involving region and boundary functionals and revisits this problem using the notion of a shape derivative and shows that the same equations can be elegantly derived without going through the unnatural step of converting the region integrals into boundary integrals. Expand
Statistical shape influence in geodesic active contours
  • M. Leventon, W. Grimson, O. Faugeras
  • Mathematics, Computer Science
  • Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)
  • 2000
A novel method of incorporating shape information into the image segmentation process is presented. We introduce a representation for deformable shapes and define a probability distribution over theExpand
Shape statistics in kernel space for variational image segmentation
TLDR
Applications of the nonlinear shape statistics in segmentation and tracking of 2D and 3D objects demonstrate that the segmentation process can incorporate knowledge on a large variety of complex real-world shapes. Expand
An SL(2) Invariant Shape Median
TLDR
A generalization of the median for shapes in the plane is introduced and an existence result can be established in the class of sets of finite perimeter, which is a powerful averaging concept on sets of vector data in finite dimensions. Expand
Fast Global Minimization of the Active Contour/Snake Model
TLDR
This paper proposes to unify three well-known image variational models, namely the snake model, the Rudin–Osher–Fatemi denoising model and the Mumford–Shah segmentation model, and establishes theorems with proofs to determine a global minimum of the active contour model. Expand
Approximations of Shape Metrics and Application to Shape Warping and Empirical Shape Statistics
TLDR
A family of smooth approximations of the distance function are proposed which are continuous with respect to the Hausdorff topology, and hence withrespect to the other two topologies, and compute the corresponding Gâteaux derivatives. Expand
Region-Based Active Contour with Noise and Shape Priors
TLDR
The general framework of exponential family is used as a prior model for noise and shape priors in region-based active contours and translation and scale invariant Legendre moments are considered to incorporate the shape prior. Expand
...
1
2
3
4
5
...