Using Dynamic Programming for Solving Variational Problems in Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
On active contour models and balloons
CVGIP: Image Understanding
Shape Modeling with Front Propagation: A Level Set Approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
Dynamic Programming for Detecting, Tracking, and Matching Deformable Contours
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer Assisted Quantitative Analysis of Deformities of the Human Spine
MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
Hi-index | 0.01 |
Spine boundary is one of the key landmarks for quantifying deformities of pathological spines. In this paper, we propose a new approach to the detection of spine boundaries. We integrate two dynamic programming procedures into a single one to enable constraints between the left and right parts of the boundary to be enforced. This dual dynamic programming approach detects two boundary curves at the same time. Moreover we propose to use angular limits in a piecewise linear model as a new smoothness constraint. This leads to a computationally efficient way of introducing high order priors. Experimental results show a very robust performance of the method.