2 D SHAPE SEGMENTATION : A NEW APPROACHKenong
نویسندگان
چکیده
We propose a novel approach to 2D shape segmentation by simulating the electrical charge density distribution on a 2D contour. The method is unique and invariant with respect to scale, translation and rotation. It computes signiicant 2D shape features by considering global data and is easily extensible to the 3D case. R esum e Nous proposons une nouvelle approche au probl eme de la segmentation 2D par une m ethode de simulation de distribution de densit e de charges electriques sur un contour bi-dimensionnel. La m ethode reste unique et invariante par rapport aux changements d' echelles, aux translations et aux rotations. Elle calcule les caract eristiques signi-catives des formes 2D en consid erant l'ensemble des donn ees. De plus, ce travail peut ^ etre facilement etendu aux formes tri-dimensionnelles.
منابع مشابه
Mesh Segmentation via Recursive and Visually Salient Spectral Cuts
We develop a new mesh segmentation algorithm via recursive spectral 2-way cut and Nyström approximation. The cut is performed on 1-D spectral embeddings, which are efficiently computed from appropriately defined distances between the set of mesh faces and only two sample faces. By using a novel sampling scheme based on shape context and a line search over the 1-D embeddings to locate the most p...
متن کاملThree-dimensional Model-based Segmentation of Brain MRI
This paper presents a new technique for the automatic model-based segmentation of 3-D objects from volumetric image data. The development closely follows the seminal work of Cootes et al. [5] but presents various new solutions to come up with a true 3-D technique rather than a sliceby-slice 2-D processing. The segmentation system includes both the building of statistical models and the automati...
متن کاملAppearance-based segmentation of medial temporal lobe structures.
A new paradigm for the characterization of structure appearance is proposed, based on a combination of gray-level MRI intensity data and a shape descriptor derived from a priori principal components analysis of 3D deformation vector fields. Generated without external intervention, it extends into 3D more classic, 2D manual landmark-based shape models. Application of this novel concept led to a ...
متن کاملSegmentation of 2-D and 3-D objects from MRI volume data using constrained elastic deformations of flexible Fourier contour and surface models
This paper describes a new model-based segmentation technique combining desirable properties of physical models (snakes), shape representation by Fourier parametrization, and modelling of natural shape variability. Flexible parametric shape models are represented by a parameter vector describing the mean contour and by a set of eigenmodes of the parameters characterizing the shape variation. Us...
متن کاملDatabase-Guided Simultaneous Multi-slice 3D Segmentation for Volumetric Data
Automatic delineation of anatomical structures in 3-D volumetric data is a challenging task due to the complexity of the object appearance as well as the quantity of information to be processed. This makes it increasingly difficult to encode prior knowledge about the object segmentation in a traditional formulation as a perceptual grouping task. We introduce a fast shape segmentation method for...
متن کامل