Abstract
In this paper we demonstrate how to embed label consistency constraints into point correspondence matching. We make two contributions. First, we show how the point proximity matrix can be incorporated into the support function for probabilistic relaxation. Second we show how the label probabilities delivered by relaxation labelling can be used to gate the kernel matrix for articulated point pattern matching. The method is evaluated on synthetic and real-world data, where the label compatibility process is demonstrated to improve the correspondence process.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Training Models of Shape from Sets of Examples. In: Proceedings BMVC 1992, pp. 9–18 (1992)
Kittler, J., Hancock, E.R.: Combining Evidence In Probabilistic Relaxation. International Journal of Pattern Recognition And Artificial Inteligence 3(1), 29–51 (1989)
Pappu, S., Gold, S., Rangarajan, A.: A framework for non-rigid matching and correspondence. In: Advances in Neural Information Processing Systems, vol. 8, pp. 795–801 (1996)
Pelillo, M., Refice, M.: Learning Compatibility Coefficients for Relaxation Labeling Processes. IEEE Trans. PAMI 16(9), 933–945 (1994)
Pilu, M.: A direct method for stereo correspondence based on singular value decomposition. In: IEEE CVPR (1997)
Rosenfeld, A., Hummel, R., Zucker, S.: Scene labeling by relaxation operations. IEEE Trans. Systems. Man and Cybernetics 6, 420–433 (1976)
Schölkopf, B., Smola, A.J., Müller, K.R.: Nonlinear component analysis as a kernel eigenvvalue problem. Neural Computation 10, 1299–1319 (1998)
Scott, G.L., Longuet-Higgins, H.C.: An Algorithm for Associating the Features of Two Images. Proc. Royal Soc. London Series B 244, 21–26 (1991)
Shapiro, L.S., Brady, J.M.: Feature-Based Correspondence - An Eigenvector Approach. Image and Vision Computing 10, 283–288 (1992)
Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: A factorization method. International Journal of Computer Vision 9(2), 137–154 (1992)
Wang, H.-F., Hancock, E.R.: A kernel view of spectral point pattern matching. In: Fred, A., Caelli, T.M., Duin, R.P.W., Campilho, A.C., de Ridder, D. (eds.) SSPR&SPR 2004. LNCS, vol. 3138, pp. 361–369. Springer, Heidelberg (2004)
Wilson, R.C., Hancock, E.R.: Structural Matching by Discrete Relaxation. IEEE Trans. PAMI 19(6), 634–648 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, H., Hancock, E.R. (2005). Improving Correspondence Matching Using Label Consistency Constraints. In: Marques, J.S., Pérez de la Blanca, N., Pina, P. (eds) Pattern Recognition and Image Analysis. IbPRIA 2005. Lecture Notes in Computer Science, vol 3522. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11492429_29
Download citation
DOI: https://doi.org/10.1007/11492429_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26153-7
Online ISBN: 978-3-540-32237-5
eBook Packages: Computer ScienceComputer Science (R0)