![](bg6.png)
Table 3: The registration errors.
Object Full Object Partial Object
King 0.2174 0.0001
Rook 0.0001 0.0844
Queen 0.0001 0.0001
Bishop 0.1011 0.0460
5 CONCLUSION AND FUTURE
WORK
L-SEPMap is a surface signature-based representa-
tion scheme that is orientation-independent and can
be used to align surfaces under rigid transformation.
The experimental results demonstrate the effective-
ness of the proposed technique and the ability to han-
dle general registration problem of full and partial ob-
jects. Several items will be considered in future work.
Among those items are , studying the impact of noise
on the discrimination effectiveness of the L-SEPMap,
experimenting with clutter scenes and different trian-
gulation sampling, applying the L-SEPMap scheme
to the 3D segmentation problem, and extending the
matching algorithm to handle uniform scaling.
REFERENCES
Bernardini, F., Martin, I., Mittleman, J., Rushmeier, H.,
and Taubin, G. (2002). Building a digital model
of michelangelo’s florentine pieta. IEEE Computer
Graphics & Applications, 22(1):59–67.
Besl, P. and McKay, N. (1992). A method for registration
of 3-d shapes. IEEE Trans. on PAMI, 14(2):239–256.
Blais, G. and Levine, M. D. (1995). Registering multiview
range data to create 3d computer objects. IEEE Trans.
on PAMI, 17(8):820–824.
Chen, H. and Bhanu, B. (August 2004). 3d free-form ob-
ject recognition in range images using local surface
patches. In Proc. of the 17th Int. Conf. on Pattern
Recognition, pages 524–530, Cambridge, UK.
Chua, C. S. and Jarvis, R. (1997). Point signatures: A
new representation for 3-d object recognition. Inter-
national Journal of Computer Vision, 25(1):63–85.
Correa, S. and Shapiro, L. (2001). A new signature-based
method for efficient 3-d object recognition. In Proc.
IEEE CVPR, volume 1, pages 769–776.
Eggert, D. W., Lorusso, A., and Fisher, R. B. (1997). Es-
timating 3d rigid body transformations: a comparison
of four major algorithms. Machine Vision and Appli-
cations, 9:272–290.
Fan, Y., Jiang, T., and Evans, D. (2002). Medical image
registration using parallel genetic algorithms. LNCS
(Applications of Evolutionary Computing), 2279:304–
314.
Hemayed, E. (July 2003). A scalable approach for 3d
mesh generation. In Proc. of the 7th World Multi-
Conference on Systemics, Cybernetics and Informat-
ics, Oralndo, FL.
Ikeuchi, K. and Sato, Y., editors (2001). Modeling From
Reality. Kluwer Academic Publishers.
Johnson, J. and Hebert, M. (1999). Using spin images
for efficient object recognition in cluttered 3d scenes.
IEEE Trans. on PAMI, 21(5):433–449.
Okatani, I. and Sugimoto, A. (2004). Registration of
range images that preserves local surface structures
and color. In Proc. of the 2nd International Sym-
posium on 3D Data Processing, Visualization, and
Transmission (3DPVT’04), pages 789–796.
Robertson, C. and Fisher, R. (2002). Parallel evolutionary
registration of range data. Computer Vision and Image
Understanding, 87(1):39–50.
Rusinliewicz, S. and Levoy, M. (2001). Efficient variants
of the icp algorithm. In Proc. of the 3th Int. Conf. on
3-D Digital Imaging and Modeling, volume 1, pages
145–152.
Sharp, G. C., Lee, S. W., and Wehe, D. K. (2002). ICP
registration using invariant features. IEEE Trans. on
PAMI, 24(1):90–102.
Silva, L., Bellon, O. R. P., and Boyer, K. L. (2005). Pre-
cision range image registration using a robust surface
interpenetration measure and enhanced genetic algo-
rithms. IEEE Trans. on PAMI, 27(5):762–776.
Stein, F. and Medioni, G. (1992). Structural indexing: ef-
ficient 3-d object recognition. IEEE Trans. on PAMI,
14(2):125–145.
Sun, Y., Paik, J., Koschan, A., Page, D. L., and Abidi, M. A.
(2003). Point fingerprint: A new 3-d object represen-
tation scheme. IEEE Trans. On Systems, Man and Cy-
bernetics - Part B: Cybernetics, 33(4):712–717.
Williams, J. and Bennamoun, M. (2001). Simultaneous reg-
istration of multiple corresponding point sets. Com-
puter Vision and Image Understanding, 81(1):117–
142.
Yamany, S. M. and Farag, A. A. (2002). Surface sig-
natures: An orientation independent free-form sur-
face representation scheme for the purpose of objects
registration and matching. IEEE Trans. on PAMI,
24(8):1105–1120.
Zhang, D. and Herbert, M. (1999). Harmonic maps and
their applications in surface matching. In Proc. IEEE
Conf. CVPR, volume 2, pages 524–530.
Zhang, H., Hall-Holt, O., and Kaufman, A. (June 2004).
Range image registration via probability field. In
Proc. of the Computer Graphics International, pages
546–552, Crete, Greece.
Zhang, Z. (1994). Iterative point matching for registra-
tion of freeform curves and surfaces. IEEE Trans. on
PAMI, 13(2):119–152.
VISAPP 2006 - IMAGE UNDERSTANDING
148