Abstract
This paper addresses the problem of learning shape models from examples. The contributions are twofold. First, a comparative study is performed of various methods for establishing shape correspondence - based on shape decomposition, feature selection and alignment. Various registration methods using polygonal and Fourier features are extended to deal with shapes at multiple scales and the importance of doing so is illustrated. Second, we consider an appearance-based modeling technique which represents a shape distribution in terms of clusters containing similar shapes; each cluster is associated with a separate feature space. This representation is obtained by applying a novel simultaneous shape registration and clustering procedure on a set of training shapes. We illustrate the various techniques on pedestrian and plane shapes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
A. Baumberg and D. Hogg. Learning flexible models from image sequences. In Proc. of the ECCV, pages 299–308, 1994.
T. Cootes, C. Taylor, D. Cooper, and J. Graham. Active shape models-their training and applications. CVIU, 61(1):38–59, 1995.
N. Duta, A. Jain, and M.-P. Dubuisson-Jolly. Learning 2d shape models. In Proc. of the ICCV, pages 8–14, Kerkyra, Greece, 1999.
D. M. Gavrila and V. Philomin. Real-time object detection for ”smart“ vehicles. In Proc. of the ICCV, pages 87–93, Kerkyra, Greece, 1999.
Y. Gdalyahu and D. Weinshall. Flexible syntatic matching of curves and its application to automatic hierarchical classification of silhouettes. IEEE Trans. on PAMI, 21(12):1312–1328, December 1999.
C. Goodall. Procrustes methods in the statistical analysis of shape. J. Royal Statistical Soc. B, 53(2):285–339, 1991.
J. Gorman, R. Mitchell, and F. Kuhl. Partial shape recognition using dynamic programming. IEEE Trans. on PAMI, 10(2):257–266, 1988.
T. Heap and D. Hogg. Improving the specificity in PDMs using a hierarchical approach. In Proc. of the BMVC, Colchester, UK, 1997. BMVA Press.
A. Hill, C. Taylor, and A. Brett. A framework for automatic landmark identification using a new method of nonrigid correspondence. IEEE Trans. on PAMI, 22(3): 241–251, March 2000.
D. Jacobs, D. Weinshall, and Y. Gdalyahu. Condensing image databases when retrieval is based on non-metric distances. In Proc. of the IEEE CVPR Conf., pages 596–601, Ft. Collins, U.S.A., 1999.
H.-C. Liu and M. Srinath. Partial shape classification using contour matching in distance transformation. IEEE Trans. on PAMI, 12(11):1072–1079, November 1990.
F. Mokhtarian and A. K. Mackworth. A theory of multiscale, curvature-based shape representation for planar curves. IEEE Trans. on PAMI, 14(8):789–805, 1992.
A. Rattarangsi and R. T. Chin. Scale-based detection of corners of planar curves. IEEE Trans. on PAMI, 14(4):430–449, 1992.
P. Zhu and P. Chirlian. On critical point detection of digital shape. IEEE Trans. on PAMI, 17(8):737–748, 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gavrila, D., Giebel, J., Neumann, H. (2001). Learning Shape Models from Examples. In: Radig, B., Florczyk, S. (eds) Pattern Recognition. DAGM 2001. Lecture Notes in Computer Science, vol 2191. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45404-7_49
Download citation
DOI: https://doi.org/10.1007/3-540-45404-7_49
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42596-0
Online ISBN: 978-3-540-45404-5
eBook Packages: Springer Book Archive