Structural graph matching using the EM algorithm and singular value decomposition

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volumn 23, Issue 10, 2001, Pages 1120-1136

  Luo, Bin ^a,b   Hancock, Edwin R ^a  

^a UNIVERSITY OF YORK   (United Kingdom)

^b ANHUI UNIVERSITY   (China)

Author keywords

Delaunay triangulations; EM algorithm; Inexact graph matching; Matrix factorization; Mixture models

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; DATA STRUCTURES; GRAPH THEORY; MAXIMUM LIKELIHOOD ESTIMATION; PROBABILITY DISTRIBUTIONS;

GRAPH MATCHING;

PATTERN MATCHING;

EID: 0035481405     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/34.954602     Document Type: Article

References (52)

1. A versatile computer-controlled assembly system
2. Relational descriptions in picture processing
3. Structural stereopsis for 3D vision
4. Training stochastic model recognition algorithms can lead to maximum mutual information estimation of parameters
5. Error correcting graph matching: On the influence of the underlying cost function
6. Inexact graph matching for structural pattern recognition
7. Recent advances in graph matching
8. A graph distance metric based on the maximal common subgraph
9. Structural matching in computer vision using probabilistic relaxation
10. Spectral graph theory
11. Graph matching with a dual- step EM algorithm
12. Inexact graph matching with genetic search
13. Maximum-likelihood from incomplete data via the EM algorithm
14. An image understanding system using attributed symbolic representation and inexact graph-matching
15. Softening discrete relaxation
16. An energy function and continuous edit process for graph matching
17. Symbolic graph matching with the EM algorithm
18. The representation and matching of pictorical structures
19. A graduated assignment algorithm for graph matching
20. Symbolic image matching by simulated annealing
21. Pairwise data clustering with deterministic annealing
22. Stereo correspondence through feature grouping and maximal cliques
23. Polyhedral object recognition by indexing
24. Statistical learning, localization, and identification of objects
25. Corner detection via topographic analysis of vector potential
26. Registering incomplete radar images with the EM algorithm
27. Matching hierarchical structures using association graphs
28. Replicator equations, maximal cliques, and graph isomorphism
29. A new method for mapping optimisation problems
30. A novel optimizing network architecture with applications
31. A distance measure between attributed relational graphs for pattern recognition
32. An algorithm for associating the features of 2 images
33. Modelbase partitioning using property matrix spectra
34. A metric for comparing relational descriptions
35. Feature-based correspondence - An eigenvector approach
36. Indexing using a spectral encoding of topological structure
37. Constrained nets for graph matching and other quadratic assignment problems
38. Pattern-recognition by graph matching using the potts MFT neural networks
39. Indexing based on edit-distance matching of shape graphs
40. An algorithm for subgraph isomorphism
41. An eigen decomposition approach to weighted graph matching problems
42. Mixture models and EM algorithms for object, recognition within compositional hierarchies
43. Map model matching
44. Deterministic search for relational graph matching
45. Structural matching by discrete relaxation
46. Entropy and distance of random graphs with application to structural pattern recognition
47. Statistical physics algorithms that converge
48. Statistical physics, mixtures of distributions, and the EM algorithm