SIGGRAPH '87 Proceedings of the 14th annual conference on Computer graphics and interactive techniques
Multiresolution elastic matching
Computer Vision, Graphics, and Image Processing
On active contour models and balloons
CVGIP: Image Understanding
Elastic matching of multimodality medical images
CVGIP: Graphical Models and Image Processing
A fast algorithm for active contours and curvature estimation
CVGIP: Image Understanding
A survey of image registration techniques
ACM Computing Surveys (CSUR)
Deformable contours: modeling, extraction, detection and classification
Deformable contours: modeling, extraction, detection and classification
A new general triangulation method for planar contours
SIGGRAPH '82 Proceedings of the 9th annual conference on Computer graphics and interactive techniques
Bayesian learning for cardiac SPECT image interpretation
Artificial Intelligence in Medicine
Hi-index | 0.00 |
This paper describes a new approach of surface/contour registration based on a physically deformable model. No prior knowledge about the types of geometric transformation is required for registration. Instead, our approach views the surface as made of elastic material that will change shape in response to the applied external force. The registration of two surfaces/contours is the deformation process of one shape towards the other governed physical laws. Before the deformation, the two shapes are roughly registered with a global affine transformation. The physically deformable model is then applied to deform one shape to match the other. The point correspondences between the two shapes are established when one shape is finally deformed to the other. In the 2D case, the model is similar to the active contour model but registration is formulated as an equilibrium problem instead of minimization problem. The result is a set of decoupled linear system equations that are easy to solve. It is also shown that, because of physical constraints imposed, our model is an improved version of Burr's dynamic contour model. Experimental results are presented to demonstrate the performance of the model.