Abstract
A novel method is presented to evaluate the similarity of shapes based on the curvature features and their distribution. Firstly the curvature information is used to define the curvature features, which are learned and searched by the proposed statistic method. Secondly the structural features of each pair are measured, so that the distribution of the curvature feature can be further measured. Taking both advantages of the local shape context analysis and the global feature distances optimization, our method can endure large nonrigid distortion and occlusion. The experiments, which have been implemented on the MPEG-7 shape database, show that this method is efficient and robust under certain shape distortion. Another experiment on the abnormal behavior detection shows its potential in shape detection, motion tracking, image retrieving and the related areas.
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
Veltkamp, R.C., Hagedoorn, M.: State-of-the-art in shape matching. Technichal Report UU-CS (Ext. r. no. 1999-27), Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands (1999)
Zhang, D., Lu, G.: Evaluation of MPEG-7 shape descriptors against other shape descriptors. Multimedia Systems 9(1) (2003)
Mokhtarian, F.: Silhouette-based isolated object recognition through curvature scale space. IEEE Transactions on Pattern Analysis and Machine Intelligence 17(5), 539–544 (1995)
Zhang, D., Lu, G.: A Comparison Of Shape Retrieval Using Fourier Descriptors And Short-Time Fourier Descriptors. In: Proceeding of The Second IEEE Pacific-Rim Conference on Multimedia, Beijing, China (October 2001)
Chellappa, R., Bagdazian, R.: Fourier Coding of Image Boundaries. IEEE Transactions on Pattern Analysis and Machine Intelligence 6(1), 102–105 (1984)
Tieng, Q., Boles, W.: Recognition of 2D Object Contours Using the Wavelet Transform Zero-Crossing Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(8), 910–916 (1997)
Thayananthan, A., Stenger, B., Torr, P.H.S., Cipolla, R.: Shape Context and Chamfer Matching in Cluttered Scenes. IEEE Conference on Computer Vision and Pattern Recognition, 127–133 (2003)
Adamek, T., Connor, N.: A Multiscale Representation Method for Nonrigid Shapes With a Single Closed Contour. IEEE Transaction on Circuits and Systems for Video Technology 14(5) (2004)
Tu, Z., Yuille, A.L.: Shape Matching and Recognition: Using Generative Models and Informative Features. In: European Conference on Computer Vision (2004)
Sebastian, T.B., Klein, P.N., Kimia, B.B.: On Aligning Curves. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(1), 116–124 (2003)
Stark, M., Schiele, B.: How Good are Local Features for Classes of Geometric Objects. In: Internatianl Conference of Computer Vision, Rio de Janeiro, Brazil (October 2007)
Opelt, A., Pinz, A., Zisserman, A.: A Boundary-Fragment-Model for Object Detection. In: European Conference on Computer Vision, Graz, Austria (May 2006)
Witkin, A.P.: Scale Space filtering. In: Proceeding of 8th International Joint Confference of Artificial Intelligence (1983)
Abbasi, S., Mokhtarian, F., Kittler, J.: Curvature scale space image in shape similarity retrieval. Multimedia Systems 7(6), 467–476 (1999)
Petrakis, E., Diplaros, A., Milios, E.: Matching and Retrieval of Distorted and Occluded Shapes Using Dynamic Programming. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(11) (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, Y., Li, F., Huang, T. (2008). Curvature Feature Based Shape Analysis. In: Huang, DS., Wunsch, D.C., Levine, D.S., Jo, KH. (eds) Advanced Intelligent Computing Theories and Applications. With Aspects of Theoretical and Methodological Issues. ICIC 2008. Lecture Notes in Computer Science, vol 5226. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87442-3_52
Download citation
DOI: https://doi.org/10.1007/978-3-540-87442-3_52
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87440-9
Online ISBN: 978-3-540-87442-3
eBook Packages: Computer ScienceComputer Science (R0)