A variational segmentation framework using active contours and thresholding
SIP '07 Proceedings of the Ninth IASTED International Conference on Signal and Image Processing
Liver segmentation using sparse 3D prior models with optimal data support
IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
Simultaneous object classification and segmentation with high-order multiple shape models
IEEE Transactions on Image Processing
Is a single energy functional sufficient? adaptive energy functionals and automatic initialization
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
On the Length and Area Regularization for Multiphase Level Set Segmentation
International Journal of Computer Vision
Diffusion maps as a framework for shape modeling
Computer Vision and Image Understanding
SIAM Journal on Imaging Sciences
An Elasticity-Based Covariance Analysis of Shapes
International Journal of Computer Vision
Particle filtering with dynamic shape priors
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part I
Comparative analysis of kernel methods for statistical shape learning
CVAMIA'06 Proceedings of the Second ECCV international conference on Computer Vision Approaches to Medical Image Analysis
ACM Transactions on Graphics (TOG) - SIGGRAPH 2012 Conference Proceedings
Hi-index | 0.01 |
Segmentation involves separating an object from the background. In this work, we propose a novel segmentation method combining image information with prior shape knowledge, within the level-set framework. Following the work of Leventon et al., we revisit the use of principal component analysis (PCA) to introduce prior knowledge about shapes in a more robust manner. To this end, we utilize Kernel PCA and show that this method of learning shapes outperforms linear PCA, by allowing only shapes that are close enough to the training data. In the proposed segmentation algorithm, shape knowledge and image information are encoded into two energy functionals entirely described in terms of shapes. This consistent description allows to fully take advantage of the Kernel PCA methodology and leads to promising segmentation results. In particular, our shape-driven segmentation technique allows for the simultaneous encoding of multiple types of shapes, and offers a convincing level of robustness with respect to noise, clutter, partial occlusions, or smearing.