Abstract
This paper presents an unsupervised range image segmentation based on Kohonen neural network. At first, the derivative and partial derivative of each point are calculated and the normal in each points is gotten. With the character vectors including normal and range value, self-organization map is introduced to cluster. The normal analysis is used to eliminate over-segmentation and the last result is gotten. This method avoid selecting original seeds and uses fewer samples, moreover computes rapidly. The experiment shows the better performance.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
J. Berkmann, T. Caeli, Computation of surface geometry and segmentation using covariance techniques, IEEE Trans. on PAMI, 16(1994)11, 1114–1116.
S. M. Bhandarkar, A. Siebert, An intergrated system for range image understanding, Inter. J. of Pattern Recognition and Artificial Intelligence, 6(1992)5, 913–953.
O. D. Faugeras, M. Hebert, E. Pauchon, Segmentation of range data into planar and quadratic patches, Proc. Third Computer Vision Pattern Recognition, 1983, 8–13.
Besl, Jain, Segmentation through variable-order surface fitting, IEEE Trans. on PAMI, 10(1988)2, 167–191.
S. Ghosal, et al., Range surface characterization and segmentation using neural networks, Pattern Recognition, 28(1995)5, 711–727.
Author information
Authors and Affiliations
About this article
Cite this article
Zou, N., Liu, J., Zhou, M. et al. Segmentation of range image based on Kohonen neural network. J. of Electron.(China) 18, 237–241 (2001). https://doi.org/10.1007/s11767-001-0033-4
Issue Date:
DOI: https://doi.org/10.1007/s11767-001-0033-4