A Method for Registration of 3-D Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
A survey of image registration techniques
ACM Computing Surveys (CSUR)
A Graduated Assignment Algorithm for Graph Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Dynamics of Nonlinear Relaxation Labeling Processes
Journal of Mathematical Imaging and Vision
Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
A new point matching algorithm for non-rigid registration
Computer Vision and Image Understanding - Special issue on nonrigid image registration
Replicator Equations, Maximal Cliques, and Graph Isomorphism
Neural Computation
A Laplacian spectral method for stereo correspondence
Pattern Recognition Letters
Structure-oriented contour representation and matching for engineering shapes
Computer-Aided Design
Spectral Correspondence Using the TPS Deformation Model
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Similarity Invariant Delaunay Graph Matching
SSPR & SPR '08 Proceedings of the 2008 Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Robust feature point matching by preserving local geometric consistency
Computer Vision and Image Understanding
Automated geospatial conflation of vector road maps to high resolution imagery
IEEE Transactions on Image Processing
Chinese Calligraphy Character Image Synthesis Based on Retrieval
PCM '09 Proceedings of the 10th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
A quadratic programming based cluster correspondence projection algorithm for fast point matching
Computer Vision and Image Understanding
Using the Particle Filter Approach to Building Partial Correspondences Between Shapes
International Journal of Computer Vision
Rotation invariant non-rigid shape matching in cluttered scenes
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
The thin plate spline robust point matching (TPS-RPM) algorithm: A revisit
Pattern Recognition Letters
Fast brain matching with spectral correspondence
IPMI'11 Proceedings of the 22nd international conference on Information processing in medical imaging
IPMI'11 Proceedings of the 22nd international conference on Information processing in medical imaging
Registering sets of points using Bayesian regression
Neurocomputing
Robust point matching revisited: a concave optimization approach
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Computational Intelligence and Neuroscience - Special issue on Computational Intelligence in Biomedical Science and Engineering
Efficient and scalable 4th-order match propagation
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Multi-feature structure fusion of contours for unsupervised shape classification
Pattern Recognition Letters
Diffeomorphic spectral matching of cortical surfaces
IPMI'13 Proceedings of the 23rd international conference on Information Processing in Medical Imaging
Robust point pattern matching based on spectral context
Pattern Recognition
Hi-index | 0.14 |
In previous work on point matching, a set of points is often treated as an instance of a joint distribution to exploit global relationships in the point set. For nonrigid shapes, however, the local relationship among neighboring points is stronger and more stable than the global one. In this paper, we introduce the notion of a neighborhood structure for the general point matching problem. We formulate point matching as an optimization problem to preserve local neighborhood structures during matching. Our approach has a simple graph matching interpretation, where each point is a node in the graph, and two nodes are connected by an edge if they are neighbors. The optimal match between two graphs is the one that maximizes the number of matched edges. Existing techniques are leveraged to search for an optimal solution with the shape context distance used to initialize the graph matching, followed by relaxation labeling updates for refinement. Extensive experiments show the robustness of our approach under deformation, noise in point locations, outliers, occlusion, and rotation. It outperforms the shape context and TPS-RPM algorithms on most scenarios.