Paper Info
Title
Joint Segmentation and Shape Regularization With a Generalized Forward–Backward Algorithm
Abstract
This paper presents a method for the simultaneous segmentation and regularization of a series of shapes from a corresponding sequence of images. Such series arise as time series of 2D images when considering video data, or as stacks of 2D images obtained by slicewise tomographic reconstruction. We first derive a model where the regularization of the shape signal is achieved by a total variation prior on the shape manifold. The method employs a modified Kendall shape space to facilitate explicit computations together with the concept of Sobolev gradients. For the proposed model, we derive an efficient and computationally accessible splitting scheme. Using a generalized forward–backward approach, our algorithm treats the total variation atoms of the splitting via proximal mappings, whereas the data terms are dealt with by gradient descent. The potential of the proposed method is demonstrated on various application examples dealing with 3D data. We explain how to extend the proposed combined approach to shape fields which, for instance, arise in the context of 3D+t imaging modalities, and show an application in this setup as well.
Year
DOI
Venue
2016
10.1109/TIP.2016.2567068
IEEE Transactions on Image Processing
Keywords
Field
DocType
Shape,Manifolds,Active contours,Image segmentation,Computational modeling,Three-dimensional displays,TV
Computer vision,Active shape model,Tomographic reconstruction,Gradient descent,Scale-space segmentation,Forward–backward algorithm,Segmentation,Image segmentation,Regularization (mathematics),Artificial intelligence,Mathematics
Journal
Volume
Issue
ISSN
25
7
1057-7149
Citations 
PageRank 
References 
3
0.38
36
Authors
5
Name
Order
Citations
PageRank
Anca Stefanoiu130.38
andreas weinmann213812.81
Martin Storath313812.69
Nassir Navab46594578.60
Maximilian Baust515519.15