A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Recovery of Parametric Models from Range Images: The Case for Superquadrics with Global Deformations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Dynamic 3D Models with Local and Global Deformations: Deformable Superquadrics
IEEE Transactions on Pattern Analysis and Machine Intelligence
A unified distance transform algorithm and architecture
Machine Vision and Applications
Multiresolution stochastic hybrid shape models with fractal priors
ACM Transactions on Graphics (TOG) - Special issue on interactive sculpting
New feature points based on geometric invariants for 3D image registration
International Journal of Computer Vision
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Superquadrics and Free-Form Deformations: A Global Model to Fit and Track 3D Medical Data
CVRMed '95 Proceedings of the First International Conference on Computer Vision, Virtual Reality and Robotics in Medicine
Localization of 3D Anatomical Point Landmarks in 3D Tomographic Images Using Deformable Models
MICCAI '00 Proceedings of the Third International Conference on Medical Image Computing and Computer-Assisted Intervention
3D human face description: landmarks measures and geometrical features
Image and Vision Computing
A pose-independent method for 3D face landmark formalization
Computer Methods and Programs in Biomedicine
3D human face soft tissues landmarking method: An advanced approach
Computers in Industry
Geometry-based 3D face morphology analysis: soft-tissue landmark formalization
Multimedia Tools and Applications
| Hi-index | 0.00 |
Existing approaches to the extraction of 3D point landmarks based on parametric deformable models suffer from their dependence on a good model initialization to avoid local suboptima during model fitting. Our main contribution to increasing the robustness of model fitting against local suboptima is a novel hybrid optimization algorithm combining the advantages of both the conjugate gradient (cg-)optimization method (known for its time efficiency) and genetic algorithms (exhibiting robustness against local suboptima). It has to be stressed, however, that the scope of applicability of this nonlinear optimization method is not restricted to model fitting problems in medical image analysis. We apply our model fitting algorithm to 3D medical images depicting tip-like and saddle-like anatomical structures such as the horns of the lateral ventricles in the human brain or the zygomatic bone as part of the skull. Experimental results for 3D MR and CT images demonstrate that in comparison to a purely local cg-optimization method, the robustness of model fitting in the case of poorly initialized model parameters is significantly improved with a hybrid optimization strategy. Moreover, we compare an edge strength-based fitting measure with an edge distance-based fitting measure w.r.t. their suitability for model fitting.