Abstract
We present the concept of non-rigid matching based on demons, by reference to Maxwell's demons. We contrast this concept with the more conventional viewpoint of attraction. We show that demons and attractive points are clearly distinct for large deformations, but also that they become similar for small displacements, encompassing techniques close to optical flow. We describe a general iterative matching method based on demons, and derive from it three different non-rigid matching algorithms, one using all the image intensities, one using only contours, and one for already segmented images. At last, we present results with synthesized and real deformations, with applications to Computer Vision and Medical Image Processing.
Keywords
Matching (statistics)Computer scienceOptical flowContrast (vision)Artificial intelligenceComputer visionFlow (mathematics)Image (mathematics)AlgorithmMathematicsGeometry
Affiliated Institutions
Related Publications
Flexible syntactic matching of curves and its application to automatic hierarchical classification of silhouettes
Curve matching is one instance of the fundamental correspondence problem. Our flexible algorithm is designed to match curves under substantial deformations and arbitrary large s...
Animal: Validation and Applications of Nonlinear Registration-Based Segmentation
Magnetic resonance imaging (MRI) has become the modality of choice for neuro-anatomical imaging. Quantitative analysis requires the accurate and reproducible labeling of all vox...
Local feature view clustering for 3D object recognition
There have been important recent advances in object recognition through the matching of invariant local image features. However, the existing approaches are based on matching to...
Motion displacement estimation using an affine model for image matching
A model is developed for estimating the displacement field in spatio-temporal image sequences that allows for affine shape deformations of corresponding spatial regions and for ...
Automatic 3‐D model‐based neuroanatomical segmentation
Abstract Explicit segmentation is required for many forms of quantitative neuroanatomic analysis. However, manual methods are time‐consuming and subject to errors in both accura...
Publication Info
- Year
- 1996
- Type
- article
- Pages
- 245-251
- Citations
- 196
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
196
OpenAlex
Cite This
J.-P. Thirion
(1996).
Non-rigid matching using demons.
, 245-251.
https://doi.org/10.1109/cvpr.1996.517081
Identifiers
- DOI
- 10.1109/cvpr.1996.517081