Closed-Form Solutions for Physically Based Shape Modeling and Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Boundary Finding with Parametrically Deformable Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
An Adaptive-Focus Deformable Model Using Statistical and Geometric Information
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Priors for Level Set Representations
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
On the Incorporation of shape priors into geometric active contours
VLSM '01 Proceedings of the IEEE Workshop on Variational and Level Set Methods (VLSM'01)
Automatic and Robust Computation of 3D Medial Models Incorporating Object Variability
International Journal of Computer Vision - Special Issue on Research at the University of North Carolina Medical Image Display Analysis Group (MIDAG)
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Active mean fields: solving the mean field approximation in the level set framework
IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
| Hi-index | 0.00 |
We propose a novel parametric deformable model controlled by shape and visual appearance priors learned from a training subset of co-aligned medical images of goal objects. The shape prior is derived from a linear combination of vectors of distances between the training boundaries and their common centroid. The appearance prior considers gray levels within each training boundary as a sample of a Markov-Gibbs random field with pairwise interaction. Spatially homogeneous interaction geometry and Gibbs potentials are analytically estimated from the training data. To accurately separate a goal object from an arbitrary background, empirical marginal gray level distributions inside and outside of the boundary are modeled with adaptive linear combinations of discrete Gaussians (LCDG). Due to the analytical shape and appearance priors and a simple Expectation-Maximization procedure for getting the object and background LCDG, our segmentation is considerably faster than with most of the known geometric and parametric models. Experiments with various goal images confirm the robustness, accuracy, and speed of our approach.