Abstract
We present a theory for the recovery of the shape of a surface covered with small elements (texels). The theory is based on the apparent surface-pattern distortion in the image and fits the regularization paradigm, recently introduced in computer vision by Poggio et al., [1985]. A mapping is defined on the basis of measurement of the local distortions of a repeated unknown texture pattern due to the image projection. From this, a constraint on the gradient orientation is determined from the apparent area of a texture element. The analysis is done under an approximation of the perspective projection called paraperspective. The resulting algorithm is applied to several synthetic and real images to demonstrate its performance.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
J. Aloimonos, “Computing intrinsic images,” Ph.D thesis, Department of Computer Science, University of Rochester. 1987.
J., Aloimonos, “Shape from texture,” Biological Cybernetics, 58, pp. 345–360, 1988.
J. Aloimonos and A. Basu, “Shape and motion from contour without correspondence,” Proc IEEE Conf. Computer Vision Pattern Recog., Miami, 1986.
J. Aloimonos and D. Shulman, “Learning shape computations,” Proc. Image Understanding Workshop, vol. 2, Los Angeles, February 1987.
J. Aloimonos and M. Swain, “Shape from texture,” Proc. 9th Int. Joint Conf. Artif. Intell., pp. 926–931, Los Angeles, August 1985.
D.H., Ballard and C.M., Brown, Computer Vision. Prentice Hall: Englewood Cliffs, NJ, 1982.
J., Hadamard, Lectures on the Cauchy Problem in Linear Partial Differential Equations, Yale University Press: New Haven, 1923.
B.K.P., Horn, “Obtaining shape from shading information,” In Psychology of Computer Vision. P.H., Winston (ed.). New York: McGraw-Hill, pp. 115–155, 1975.
B.K.P., Horn, “Understanding image intensities,” Artifical Intelligence 8, pp. 201–231, 1977.
B.K.P., Horn, Robot Vision. New York: McGraw Hill, 1986.
K., Ikeuchi, “Shape from regular patterns,” Artificial Intelligence 22, pp. 49–75, 1984.
K., Ikeuchi and B.K.P., Horn, “Numerical shape from shading and occluding boundaries,” Artificial Intelligence 17, pp. 147–184. 1981.
T. Kanade and J. Kender, “Mapping image properties into shape constraints: Skewed symmetry and affine-transformable patterns,” Proc. Workshop on Picture Data Description and Management, August 1980.
K., Kanatani, “Detection of surface orientation from texture by a stereological technique,” Artifical Intelligence 23, pp. 213–237, 1984.
J. Kender, “Shape from texture,” Proc 6th Int. Joint Conf. Artif. Intell., Tokyo, 1979.
J. Kender, “Shape from texture,” Ph.D thesis, Carnegie-Mellon University, 1980.
D. Lee, “A provably convergent algorithm for shape from shading,” Proc. Image Understanding Workshop, Miami, pp. 489–496, 1985.
D., Marr, Vision, San Francisco: Freeman, 1982.
Y.K. Ohta, K. Maenobu, and T. Sakai, “Obtaining surface orientation from texels under perspective projection,”, Proc. 7th Int. Joint Conf. Artif. Intell., Vancouver, Canada, pp. 746–751, 1981.
T. Poggio, “MIT Progress in understanding images”, Proc. Image Understanding Workshop, Miami, 1985.
T. Poggio and C. Koch. “III-posed problems in early vision: from computational theory to analog networks,”, Proc. Roy. Soc. (London). B. 1985.
F.P., Preparata and M.I., Shamos, Computational Geometry: An Introduction. New York: Springer-Verlag, 1985.
S. Shafer, “Shadow geometry,” Ph.D. thesis, Carnegie-Mellon University, 1982.
D. Shulman and J. Aloimonos, “A linear theory of regularization in the presence of discontinuities,” Tech. Rept. 2011, Computer Vison Laboratory, Dept. of Computer Science, University of Maryland, 1988.
G.D. Smith, Numerical solution of Partial Differential Equations: Finite Difference Methods. Oxford University Press, 1978.
K.A. Stevens, “Surface perception from local analysis of texture and contour,” Ph.D. thesis, MIT, 1979.
A.N., Tichonov and V.Y., Arsenin, Solution of Ill-Posed Problems. Washington DC: Winston and Wiley, 1977.
G. Wahba, “Cross-validated spline methods for the estimation of functions from data on functionals.” In H.A. and H.T. David (eds.), Statistics: An Appraisal, Iowa State University, 1984.
E. Walker and t. Kanade, “Shape recovery of a solid of revolution from apparent distortions of patterns.” CMU-CS-TR 84-152. Dept. of Computer Science, Carnegie-Mellon University.
A., Witkin, “Recovering surface orientation and shape from texture.” Artificial Intelligence 17, pp. 17–45, 1981.
Author information
Authors and Affiliations
Additional information
The author is Yiannis
Rights and permissions
About this article
Cite this article
Aloimonos, J., Swain, M. Shape from patterns: Regularization. Int J Comput Vision 2, 171–187 (1988). https://doi.org/10.1007/BF00133699
Issue Date:
DOI: https://doi.org/10.1007/BF00133699