Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
Boundary Finding with Parametrically Deformable Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust epipolar geometry estimation using genetic algorithm
Pattern Recognition Letters
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Tracking Deformable Objects in the Plane Using an Active Contour Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Unified Framework to Assess Myocardial Function from 4D Images
CVRMed '95 Proceedings of the First International Conference on Computer Vision, Virtual Reality and Robotics in Medicine
Tracking Points on Deformable Objects Using Curvature Information
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Geometric active deformable models in shape modeling
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
A shape based non-rigid cardiac motion study is presented using simple fuzzy shape descriptors. The objective of this work is to evaluate the detail point wise motion trajectories from sequential contours. The shape correspondence on endocardial contour has been performed in multiple stages with well-defined, level specific curvature information. We incorporate non-uniform expansion and contraction of shape matched templates to optimize the correspondence in each level. However, final flow field evaluation is a constrained optimization problem, which results into a smooth mapping of contours. Constrained non-linear optimization with genetic algorithm has shown considerable promise in solving this problem. The results are quite consistent when correlated with the movement of implanted markers in an experimental set-up. Even though tracking contours in the reverse direction is irrelevant from a practical standpoint a good correlation between motions in either direction is observed. The algorithm has been tested over sets of 2D images to quantify the motion of left ventricle (LV) using two different imaging modalities.