ICIAR 2007: Image Analysis and Recognition pp 423-435 | Cite as
A Novel Multi-scale Representation for 2-D Shapes
Abstract
We present an original approach for 2-D shapes description. Based on a multi-scale analysis of closed contours, this method deals with the differential turning angle.
The input contour is progressively low-pass filtered by decreasing the filter bandwidth. The output contour thus becomes increasingly smooth. At each iteration of the filtering we extract the essential points from the differential turning angle of the filtered contour to generate the d-TASS map.
Experimental results show that the d-TASS map is closely related to the contour and that it is rotation, translation and scale change invariant. It is also shearing and noise resistant. This function is local-oriented and appears to be particularly suitable for pattern recognition even for those patterns that have undergone occultation.
Keywords
pattern recognition planar object contour smoothing Gaussian filter differential-turning angle curvature scale space intersection point mapPreview
Unable to display preview. Download preview PDF.
References
- 1.Kpalma, K., Ronsin, J.: Multiscale contour description for pattern recognition, Elsevier. Pattern Recognition Letters 27(13), 1545–1559 (2006)CrossRefGoogle Scholar
- 2.Feldman, J., Singh, M.: THEORETICAL NOTE: Information Along Contours and Object Boundaries. Psychological Review, The American Psychological Association 112(1), 243–252 (2005)Google Scholar
- 3.Kpalma, K., Ronsin, J.: A Multi-Scale curve smoothing for Generalised Pattern Recognition (MSGPR). In: ISSPA 2003, Paris, France, July 1-4, 2003 (2003)Google Scholar
- 4.Barenholtz, E., Cohen, E.H., Feldman, J., Singh, M.: Detection of change in shape: an advantage for concavities. Elsevier, Cognition 89, 1–9 (2003)Google Scholar
- 5.Zibreira, C., Pereira, F.: A Study of Similarity Measures for a Turning Angles-based Shape Descriptor. In: 3rd Conference on Telecommunications, conftele 2001, Figueira da Foz, April 23-24, 2001 (2001)Google Scholar
- 6.Latecki, L.J., Lakamper, R., Eckhardt, U.: Shape Descriptors for Non-rigid Shapes with a Single Closed Contour. In: CVPR. IEEE Conf. On Computer Vision and Pattern Recognition, pp. 424–429. IEEE Computer Society Press, Los Alamitos (2000)Google Scholar
- 7.Bruckstein, A.M., Rivlin, E., Weiss, I.: Recognizing objects using scale space local invariants. In: ICPR 1996. Proceedings of the 1996 International Conference on Pattern Recognition, Vienna, Austria, August 25-29, 1996, pp. 25–29 (1996)Google Scholar
- 8.Niblack, W., Yin, J.: A pseudo-distance measure for 2D shapes based on turning angle. In: ICIP 1995. Proceedings of the International Conference on Image Processing, October 23-26, 1995, vol. 3, pp. 352–355 (1995)Google Scholar
- 9.Lindeberg, T.: Scale-Space Theory in Computer Vision. Kluwer Academic Publishers, Dordrecht, Netherlands (1994)Google Scholar
- 10.Scassellati, B.: Retrieving images by 2D shape: a comparison of computation methods with human perceptual judgments. In: Niblack, W., Jain, R.C. (eds.) Proc. of SPIE, Storage and Retrieval for Image and Vision Databases II, February 1994, pp. 2–14 (1994)Google Scholar
- 11.Bruckstein, A., Katzir, N., Lindenbaum, M., Porat, M.: Similarity-Invariant Signatures for Partially Occluded Planar Shapes. IJCV 7(3), 271–285 (1992)CrossRefGoogle Scholar
- 12.Mokhtarian, F., Mackworth, A.K: A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves. In: IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI, vol. 14(8) (1992)Google Scholar
- 13.Arkin, E.M., Paul Chew, L., Huttenlocker, D.P., Kedem, K., Mitchell, J.S.B.: An efficiently computable metric for comparing polygonal shapes. IEEE Transactions on PAMI 13(3), 209–216 (1991)Google Scholar