Abstract
Tensor voting is an efficient algorithm for perceptual grouping and feature extraction, particularly for contour extraction. In this paper two studies on tensor voting are presented. First the use of iterations is investigated, and second, a new method for integrating curvature information is evaluated. In opposition to other grouping methods, tensor voting claims the advantage to be non-iterative. Although non-iterative tensor voting methods provide good results in many cases, the algorithm can be iterated to deal with more complex data configurations. The experiments conducted demonstrate that iterations substantially improve the process of feature extraction and help to overcome limitations of the original algorithm. As a further contribution we propose a curvature improvement for tensor voting. On the contrary to the curvature-augmented tensor voting proposed by Tang and Medioni, our method takes advantage of the curvature calculation already performed by the classical tensor voting and evaluates the full curvature, sign and amplitude. Some new curvature-modified voting fields are also proposed. Results show a lower degree of artifacts, smoother curves, a high tolerance to scale parameter changes and also more noise-robustness.
This research is supported in part by the German-Spanish Academic Research Collaboration Program HA 2001-0087 (DAAD, Acciones integradas Hispano-Alemanas 2002/2003), the projects TIC2001-3697-C03-02 from MCYT and IM3 from ISCIII and HGGM grants. S.F. and R.R. are supported by a MECD-FPU and a CSIC-I3P fellowships, respectively.
Chapter PDF
Similar content being viewed by others
Keywords
- Synthetic Aperture Radar
- Synthetic Aperture Radar Image
- Perceptual Grouping
- Curvature Calculation
- Full Curvature
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Hansen, T., Sepp, W., Neumann, H.: Recurrent long-range interactions in early vision. In: Wermter, S., Austin, J., Willshaw, D.J. (eds.) Emergent Neural Computational Architectures Based on Neuroscience. LNCS (LNAI), vol. 2036, pp. 127–138. Springer, Heidelberg (2001)
Medioni, G., Lee, M.-S., Tang, C.-K.: A computational framework for feature extraction and segmentation, March 2000. Elsevier Science, Amsterdam (2000)
Mingolla, E., Ross, W., Grossberg, S.: A neural network for enhancing boundaries and surfaces in synthetic aperture radar images. Neural Networks 12, 499–511 (1999)
Neumann, H., Mingolla, E.: Computational neural models of spatial integration in perceptual grouping. In: Shipley, T.F., Kellman, P.J. (eds.) From Fragments to Objects - Segmentation and Grouping in Vision, pp. 353–400. Elsevier Science, Amsterdam (2001)
Nicolescu, M., Medioni, G.: Layered 4D Representation and Voting for Grouping from Motion. IEEE Trans. P.A.M.I. 25(4), 492–501 (2003)
Parent, P., Zucker, S.: Trace inference, curvature consistency, and curve detection. IEEE Trans, P.A.M.I. 11, 823–839 (1989)
Tang, C.-K., Medioni, G.: Curvature-Augmented Tensor Voting for Shape Inference from Noisy 3D Data. IEEE Trans. P.A.M.I. 24(6), 864–868 (2002)
Tang, C.-K., Medioni, G., Lee, M.: N-dimensional tensor voting and application to epipolar geometry estimation. IEEE Trans P.A.M.I. 23(8), 829–844 (2001)
Williams, L.R., Thornber, K.K.: A comparison of measures for detecting natural shapes in cluttered backgrounds. Int. Jour. of Computer Vision 34(2/3), 81–96 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fischer, S., Bayerl, P., Neumann, H., Cristóbal, G., Redondo, R. (2004). Are Iterations and Curvature Useful for Tensor Voting?. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3023. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24672-5_13
Download citation
DOI: https://doi.org/10.1007/978-3-540-24672-5_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21982-8
Online ISBN: 978-3-540-24672-5
eBook Packages: Springer Book Archive