Abstract
We propose a new relaxation scheme for graph matching in computer vision. The main distinguishing feature of our approach is that matching is formulated as a process of eliminating unlikely candidates rather than finding the best match directly. Bayesian development leads to a robust algorithm which can be implemented in a fast and efficient manner on a neural network architecture. We illustrate the utility of the technique through comparisons with its conventional counterpart on simulated and real-world data.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Besl PJ, Jain RC. Three-dimensional object recognition. Computing Sur 1985; 17: 75–145
Boyer K, Kak A. Structural stereopsis in 3D vision. IEEE Trans PAMI 1988; 10: 144–166
Horaud R, Skordas T. Stereo correspondence through feature grouping and maximal cliques. IEEE Trans PAMI 1989; 11: 1168–1180
Christmas WJ, Kittler J, Petrou M. Structural matching in computer vision using probabilistic relaxation. IEEE Trans PAMI 1995; 17
Kittler J, Christmas WJ, Petrou M. Probabilistic relaxation for matching problems in machine vision. Proc 4th Int Conf Computer Vision 1993; 666–674
Li SZ. Matching invariant to translations, rotations and scale changes. Patt Recognition 1992; 25: 583–595
Radig B. Image sequence analysis using relational structures. Patt Recognition 1984; 17: 161–167
Shapiro LG, Haralick RM. Structural description and inexact matching. IEEE Trans PAMI 1981; 3: 504–519
Bron C, Kerbosch J. Finding all cliques in an undirected graph. Comm ACM 1973; 16(9): 575–577
Kirkpatrick S, Gelatt CD, Vecchi MP. Optimisation by simulated annealing. Science 1983; 20: 671–680
Goldberg DE. Genetic Algorithms in Search Optimisation and Machine Learning. Reading, MA: Addison-Wesley, 1989
Kittler J, Hancock ER. Probabilistic relaxation. Int J Patt Recognition and Artif Intell 1989; 3(1): 29–51
Rosenfeld A, Hummel RA, Zucker SW. Scene labelling by relaxation operations. IEEE Trans SMC 1976; 6: 400–433
Hancock ER, Kittler J. Discrete relaxation. Patt Recognition 1990; 23: 711–733
Austin J. A review of RAM-based neural networks. Proc 4th Int Conf Microelectronics for Neural Networks and Fuzzy Systems, Turin, IEEE Press, 1994; 58–66
Kohonen T, Ruohonen HC. Representation of associated data by matrix operators. IEEE Trans Computers 1973
Willshaw DJ, Buneman OP, Longet-Higgins HC. Non-holographic associative memory. Nature 1969; 222: 960–962
Austin J, Kennedy J. A hardware implementation of a binary neural network. MicroNeuro, IEEE Press, 1994
Dempster NM, Laird DB. Maximum-likelihood from incomplete data via the EM algorithm. J Roy Statistical Soc Ser B (methodological) 1977; 39: 1–38
Turner M, Austin J. Matching performance of correlation matrix memories. Neural Networks 1997; 10(a): 1637–1648
Ullman JR. An algorithm for subgraph isomorphism. J ACM 1976; 16: 31–42
Turner M. Molecular structure matching: a review. Internal Report, Department of Computer Science, University of York, 1995
Turner M, Austin J. A neural relaxation technique for chemical graph matching. Proc 5th Int Conf Arti Neural Networks, Cambridge, 1997
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Turner, M., Austin, J. Graph matching by neural relaxation. Neural Comput & Applic 7, 238–248 (1998). https://doi.org/10.1007/BF01414885
Issue Date:
DOI: https://doi.org/10.1007/BF01414885