Abstract
This paper proposes a new approach to recover the sign of local surface curvature of object from three shading images using neural network. The RBF (Radial Basis Function) neural network is used to learn the mapping of three image irradiances to the position on a sphere. Using the property that. basic five kinds of surface curvature has the different relative locations of the local five points mapped on the sphere, not only the Gaussian curvature but also the kind of curvature is directly recovered locally from the relation of the locations on the mapped points on the sphere without knowing the values of surface gradient for each point. The entire approach is non-parametric, empirical in that no explicit assumptions are made about light source directions or surface reflectance. Results are demonstrated by the experiments for real images.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
R. J. Woodham, “Gradient and curvature from the photometric stereo method, including local confidence estimation,” Journal of the Optical Society of America, A, vol. 11, pp. 3050–3068, 1994.
Y. Iwahori, H. Tanaka, R. J. Woodham, and N. Ishii, “Photometric stereo for specular surface shape based on neural network,” IEICE Transactions on Information and Systems, vol. E77-D, no. 4, pp. 498–506, 1994. (Special issue on neurocomputing).
Y. Iwahori, A. Bagheri, and R. J. Woodham, “Neural network implementation of photometric stereo,” Proc. of Vision Interface 95. (Quebec City, Canada), pp. 81–88, May 1995.
Y. Iwahori, R. J. Woodham, and A. Bagheri, “Principal components analysis and neural network implementation of photometric stereo,” in Proc. IEEE Workshop on Physics-Based Modeling in Computer Vision, pp. 117–125, June 1995.
G. Healey, S. Shafer, and L. Wolff, eds., Physics-Basal Vision: Principles and Practice (Vol. 1 Radiometry, Vol. 2 Color and Vol. 3 Shape Recovery). Boston, MA: Jones and Bartlett Publishers, Inc., 1992.
G. Healey and R. Jain, “Physics-based machine vision,” Journal of the Optical Society of America, A, vol. 11, p. 2922, 1994. (Introduction to special issue).
L. B. Wolff and J. Fan, “Segmentation of surface curvature using a photometric invariant,” Proc. of IEEE-CVPR 1994, pp. 23–30, 1994.
J. Fan and L. B. N-Folff, “Surface Curvature from Integrability.” Proc. of IEEE-CVPR 1994, pp.520–525, 1994.
S. Chen, C. F. N. Cowan, and P. M. Grant, “Orthogonal least squares learning algorithm for radial basis function networks.” IEEE Transactions on Neural Networks, vol. 2, no. 2, pp. 302–309, 1991. *** DIRECT SUPPORT *** A0008188 00003
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Iwahori, Y., Murakami, M., Woodham, R.J., Ishii, N. (1997). Sign of surface curvature from shading images using neural network. In: Chin, R., Pong, TC. (eds) Computer Vision — ACCV'98. ACCV 1998. Lecture Notes in Computer Science, vol 1351. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63930-6_102
Download citation
DOI: https://doi.org/10.1007/3-540-63930-6_102
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63930-5
Online ISBN: 978-3-540-69669-8
eBook Packages: Springer Book Archive