Abstract
We present results demonstrating that using a hierarchy of finite element vibration modes in an evolutionary deformable shape search provides a new interesting approach for the localization and segmentation of specific objects in 2D images. The design and coupling of the different levels of the shape hierarchy results in a multi–resolution shape space, which can be exploited in top–down part–based shape matching. The proposed strategy allows for segmenting complex objects from images, classification, as well as localization of the desired object under occlusions. It avoids misregistration by resolving several drawbacks inherent to standard shape–based approaches, which either cannot adequately represent non–linear variations, or rely on exhaustive prior training.
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
Biedermann, I.: Human image understanding: Recent research and a theory. Comp. Vis. Graph Imag Proc. 32, 29–73 (1985)
Pentland, A.: Recognition by parts. In: Proc. IEEE ICCV, pp. 612–620 (1987)
Ullman, S., Basri, R.: Recognition by linear combinations of models. IEEE Trans. Patt. Anal. Mach. Intell. 13(10), 992–1005 (1991)
Christmas, W., et al.: Structural matching in computer vision using probabilistic relaxation. IEEE Trans. Patt. Anal. Mach. Intell. 17(8), 749–764 (1995)
Rivlin, E., et al.: Recognition by functional parts. Comp. Vis. Imag. Understand 62(2), 164–176 (1995)
Zhu, S., Yuille, A.: Forms, A flexible object recognition and modeling system. Int. J. Comp. Vis. 20(3), 187–212 (1996)
Heap, A., Hogg, D.: Improving Specificity in PDMs using a Hierarchical Approach. In: Proc. BMVC, pp. 80–89 (1997)
Tao, H., Huang, T.: Connected vibrations: a modal analysis approach to non-rigid motion tracking. In: Proc. IEEE CVPR, pp. 1424–1426 (1998)
Al-Zubi, S., Tönnies, K.D.: Extending active shape models to incorporate a-priori knowledge about structural variability. In: Van Gool, L. (ed.) DAGM 2002, vol. 2449, p. 338. Springer, Heidelberg (2002)
Felzenszwalb, P., Huttenlocher, D.: Pictorial structures for object recognition. Int. J. Comp. Vis. 61(1), 53–79 (2003)
Weyrauch, B., et al.: Component–based Face Recognition with 3D Morphable Models. In: Proc. IEEE Face Proc. Video, pp. 1–5 (2003)
Bergner, S., et al.: Deformable structural models. In: Proc. IEEE ICIP, pp. 1875–1878 (2004)
Sigal, L., et al.: Tracking Loose–Limbed People. In: Proc. IEEE CVPR, pp. 421–428 (2004)
Zhang, J., et al.: Bayesian body localization using mixture of nonlinear shape models. In: Proc. IEEE ICCV, pp. 725–732 (2005)
Ren, X., et al.: Recovering human body configurations using pairwise constraints between parts. In: Proc. IEEE ICCV, pp. 824–831 (2005)
Zambal, S., et al.: Improving segmentation of the left ventricle using a two-component statistical model. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4190, pp. 151–158. Springer, Heidelberg (2006)
Zhe, L., et al.: Hierarchical Part–Template Matching for Human Detection and Segmentation. In: Proc. IEEE ICCV, pp. 1–8 (2007)
Srinivasan, P., Shi, J.: Bottom-up Recognition and Parsing of the Human Body. In: Proc. IEEE CVPR, pp. 1–8 (2007)
Wang, Y., Mori, G.: Multiple tree models for occlusion and spatial constraints in human pose estimation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 710–724. Springer, Heidelberg (2008)
Edelman, S.: Computational theories of object recognition. Trends Cogn. Sci. 1, 296–304 (1997)
Bienenstock, E., et al.: Compositionality, MDL Priors, and Object Recognition. In: Proc. NIPS, pp. 838–844 (1996)
Zhu, L., Yuille, A.: A Hierarchical Compositional System for Rapid Object Detection. In: Proc. NIPS (2005)
Felzenszwalb, P., Schwartz, J.: Hierarchical Matching of Deformable Shapes. In: Proc. IEEE CVPR, pp. 1–8 (2007)
Yuille, A., et al.: Feature extraction from faces using deformable templates. Int. J. Comp. Vis. 8(2), 99–111 (1992)
Felzenszwalb, P., et al.: A discriminatively trained, multiscale, deformable part model. In: Proc. IEEE CVPR, pp. 1–8 (2008)
Pentland, A., Sclaroff, S.: Closed-form solutions to physically based shape modeling and recognition. IEEE Trans. Patt. Anal. Mach. Intell. 13(7), 715–729 (1991)
Sclaroff, S., Pentland, A.: Modal matching for correspondence and recognition. IEEE Trans. Patt. Anal. Mach. Intell. 17(6), 545–561 (1995)
Cootes, T., Taylor, C.: Combining point distribution models with shape models based on finite-element analysis. Imag. Vis. Comp. 13(5), 403–409 (1995)
Kendall, D.: A survey of the statistical theory of shape. Stat. Sci. 4, 87–120 (1989)
Hill, A., Taylor, C.: Model-based image interpretation using genetic algorithms. Imag. Vis. Comp. 10(5), 295–300 (1992)
Felzenszwalb, P.: Representation and detection of deformable shapes. IEEE Trans. Patt. Anal. Mach. Intell. 27(2), 208–220 (2005)
Zheng, Z., et al.: Facial feature localization based on an improved active shape model. Inform. Sci. 178(9), 2215–2223 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Engel, K., Toennies, K.D. (2009). Hierarchical Vibrations: A Structural Decomposition Approach for Image Analysis. In: Cremers, D., Boykov, Y., Blake, A., Schmidt, F.R. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2009. Lecture Notes in Computer Science, vol 5681. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03641-5_24
Download citation
DOI: https://doi.org/10.1007/978-3-642-03641-5_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03640-8
Online ISBN: 978-3-642-03641-5
eBook Packages: Computer ScienceComputer Science (R0)