This paper presents a statistical shape model for automatic skull stripping of MR brain images. A surface model of the brain boundary is hierarchically represented by a set of overlapping surface patches, each of which has elastic properties and deformation range that is learned from a training set. The model’s deformation is hierarchical which adds robustness to local minima. Moreover, the def...

This paper describes the generation of shape primitive detecting masks and their application in measurements on shapes as well as in conditions for topology preservation as used in skeletonization. The formalism is expanded from twoto four-dimensional images and elaborates on the extension of 3D skeletonization to 4D skeletonization. 2002 Elsevier Science B.V. All rights reserved.

In this paper we introduce a new method for computing the orientation for compound shapes. If the method is applied to single component shapes the computed orientation is consistent with the shape orientation defined by the axis of the least second moment of inertia. If the new method is applied to compound shapes this is not the case, and consequently the presented method is both new and diffe...

Diabetic Retinopathy is a medical condition where the retina is damaged because fluid leaks from blood vessels into the retina. The presence of hemorrhages in the retina is the earliest symptom of diabetic retinopathy. The number and shape of hemorrhages is used to indicate the severity of the disease. Early automated hemorrhage detection can help reduce the incidence of blindness. This paper i...

Automatic construction of Shape Models from examples has been the focus of intense research during the last couple of years. These methods have proved to be useful for shape segmentation, tracking and shape understanding. In this paper novel theory to automate shape modelling is described. The theory is intrinsically defined for curves although curves are infinite dimensional objects. The theor...

Most structure from motion work assume that tracking is a separate issue from recovery of structure and motion. This paper argues that in certain cases, it helps to use the original images to refine the tracks in the course of estimating structure and motion. We illustrate this by presenting two algorithms: one for appearance-based structure from complete rotation, and another for 3-D face mode...

We provide exact shape reconstruction formulas in the spirit of the Linear Sampling method for a class of inverse problems in shape determination in the context of timeindependent partial differential equations. To this end, we prove a general theorem how, and under which assumptions, domain characterizations based on the range of the square root of an operator transform into domain characteriz...

We present a model-based method for detailed automatic building reconstruction from images. The method starts with recovering a coarse building model consisting of the main object planes. This model is upgraded by detecting deviations from the planes and fitting predefined shape primitives to these deviations to refine the geometry. The proposed method is presented on real datasets.

We aim to develop a 3D shape representation by utilizing the heat flows on 3D surfaces and the corresponding temporal dynamics of the heat flows within the diffusion period. We employ LSTM to capture the temporal dynamics of heat flows and extract joint information between different time-steps that are either consecutive or with a large interval. We incorporate a 3-layer fully-connected neural ...

To a layperson, a raindrop would have the shape of a tear drop, as often renditioned in popular media. However, to an acute individual, and as pointed out fervently by Fraser [17], a raindrop would have more of a spherical shape. The tear drop shape applies only just as the drop falls from a surface. It would then take a somewhat spherical form, and then distort to a shape like an oblate sphero...