Globally Optimal Joint Image Segmentation and Shape Matching Based on Wasserstein Modes

07/15/2014
by   Bernhard Schmitzer, et al.
0

A functional for joint variational object segmentation and shape matching is developed. The formulation is based on optimal transport w.r.t. geometric distance and local feature similarity. Geometric invariance and modelling of object-typical statistical variations is achieved by introducing degrees of freedom that describe transformations and deformations of the shape template. The shape model is mathematically equivalent to contour-based approaches but inference can be performed without conversion between the contour and region representations, allowing combination with other convex segmentation approaches and simplifying optimization. While the overall functional is non-convex, non-convexity is confined to a low-dimensional variable. We propose a locally optimal alternating optimization scheme and a globally optimal branch and bound scheme, based on adaptive convex relaxation. Combining both methods allows to eliminate the delicate initialization problem inherent to many contour based approaches while remaining computationally practical. The properties of the functional, its ability to adapt to a wide range of input data structures and the different optimization schemes are illustrated and compared by numerical experiments.

READ FULL TEXT

page 21

page 22

page 23

page 24

page 25

page 26

page 27

research
09/09/2013

Contour Manifolds and Optimal Transport

Describing shapes by suitable measures in object segmentation, as propos...
research
12/03/2013

Template-Based Active Contours

We develop a generalized active contour formalism for image segmentation...
research
04/25/2015

Adaptive Locally Affine-Invariant Shape Matching

Matching deformable objects using their shapes is an important problem i...
research
02/19/2019

2-Wasserstein Approximation via Restricted Convex Potentials with Application to Improved Training for GANs

We provide a framework to approximate the 2-Wasserstein distance and the...
research
11/21/2022

Conjugate Product Graphs for Globally Optimal 2D-3D Shape Matching

We consider the problem of finding a continuous and non-rigid matching b...
research
02/10/2018

Learning to Recommend via Inverse Optimal Matching

We consider recommendation in the context of optimal matching, i.e., we ...
research
09/29/2019

Shape Analysis via Functional Map Construction and Bases Pursuit

We propose a method to simultaneously compute scalar basis functions wit...

Please sign up or login with your details

Forgot password? Click here to reset