Clustered Signatures for Modeling and Recognizing 3D Rigid Objects

Authors: H. B. Darbandi, M. R. Ito, J. Little

Abstract:

This paper describes a probabilistic method for three-dimensional object recognition using a shared pool of surface signatures. This technique uses flatness, orientation, and convexity signatures that encode the surface of a free-form object into three discriminative vectors, and then creates a shared pool of data by clustering the signatures using a distance function. This method applies the Bayes-s rule for recognition process, and it is extensible to a large collection of three-dimensional objects.

Keywords: Object recognition, modeling, classification, computer vision.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1072068

References:

[1] Bennamoun, G.J. Mamic, "Object Recognition: Fundamentals and Case Studies," Springer, 2000.
[2] A.E. Johnson, Spin Image: "A Representation for 3D Surface Matching. PhD Thesis," Carnegie Mellon University, 1997.
[3] S. Correa, L. Shapiro, "A New Signature-Based Method for Efficient 3D Object Recognition," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1: 769-776, 2001.
[4] Stein, F.; Medioni, G.; "Structural indexing: Efficient 3D object recognition of a set of range views," IEEE transactions on pattern analysis and Machine Intelligence, 17(4):344-359, 1995.
[5] S.M. Yamany, A. Farag, "Freeform Surface Registration Using Surface Signatures," Proc. Int. Conf. on Computer Vision, 2: 1098-1104, 1999.
[6] H.B. Darbandi, M.R. Ito; J. Little, "Flatness and Orientation signature for Modeling and Matching 3D Objects," Third International Symposium on 3D Data Processing, Visualization and Transmission, 2006.
[7] Mian, A.S.; Bennamoun, M.; Owens, R. "Pattern Three-Dimensional Model-Based Object Recognition and Segmentation in Cluttered Scenes," Analysis and Machine Intelligence, IEEE Transactions on Volume 28, Issue 10, Oct. 2006 Page(s):1584 - 1601.
[8] R.J. Campbell, P.J. Flynn, "A Survey of Free-Form Object Representation and Recognition Techniques," Computer Vision and Understanding, vol. 81, pp. 166-210, 2001.
[9] B.M. Planitz, A.J. Maeder, J.A. Williams, "The correspondence framework for 3D surface matching algorithms," Computer Vision and Image Understanding, 2005. Fig. 10 Library models used in the experiments
[10] H.B. Darbandi, M.R. Ito, J. Little, "Surface Signature-Based Method for Modeling and Recognizing Free-Form Objects," 3rd International Sysposium on Visual Computing, 2007.
[11] http://shape.cs.princeton.edu/benchmark/
[12] A. Johnson; M. Herbert, "Using spin images for efficient object recognition in cluttered 3D scenes," IEEE Tr. on Pattern Analysis and Machine Intelligence. Vol. 21, N0 5. May 1999.
[13] J.D. Foley, A. van Dam; S.K. Feiner; J.F. Hughes, "Introduction to Computer Graphics," Addison-Wesley, 1993.
[14] T. Zhang, R. Ramakrishnan, M. Livny, BIRCH: "An Efficient Data Clustering Method for Very Large Databases," SIGMOD Conference 1996: 103-114.
[15] E. Alpaydin, "Introduction to Machine Learning," MIT Press, 2004.
[16] A. Johnson, M. Herbert, "Using spin images for efficient object recognition in cluttered 3D scenes," IEEE Tr. on Pattern Analysis and Machine Intelligence. Vol. 21, N0 5. May 1999.
[17] D.A. Forsyth, J. Ponce, "Computer Vision, a Modern Approach," Prentice Hall, 2003.
[18] J. B. Kuipers, "Quaternions and Rotation Sequences: A Primer with Applications to Orbits, Aerospace and Virtual Reality," Princeton University Press, 1993.
[19] H. Samet, "Depth-first k-nearest neighbor finding using the Maximum Nearest Distance estimator," IEEE Transactions, Image Analysis and Processing, 2003.