This Article 
 Bibliographic References 
 Add to: 
Shape from Texture Using Local Spectral Moments
April 1995 (vol. 17 no. 4)
pp. 333-343

Abstract—We present a non-feature-based solution to the problem of computing the shape of curved surfaces from texture information. First, the use of local spatial-frequency spectra and their moments to describe texture is discussed and motivated. A new, more accurate method for measuring the local spatial-frequency moments of an image texture using Gabor elementary functions and their derivatives is presented. Also described is a technique for separating shading from texture information, which makes the shape-from-texture algorithm robust to the shading effects found in real imagery. Second, a detailed model for the projection of local spectra and spectral moments of any surface reflectance patterns (not just textures) is developed. Third, the conditions under which the projection model can be solved for the orientation of the surface at each point are explored. Unlike earlier non-feature-based, curved surface shape-from-texture approaches, the assumption that the surface texture is isotropic is not required; surface texture homogeneity can be assumed instead. The algorithm’s ability to operate on anisotropic and non-deterministic textures, and on both smooth- and rough-textured surfaces, is demonstrated.

[1] D.G. Albrecht and W.S. Geisler,“Motion selectivity and the contrast-response function of simple cellsin the visual cortex,” Visual Neuroscience, vol. 7, pp. 531-546, 1991.
[2] J. Aloimonos and M.J. Swain,“Shape from texture,” Proc. Ninth Int’l Joint Conf. Artificial Intelligence, pp. 926-931, 1985.
[3] R. Bajcsy and L. Lieberman,“Texture gradient as a depth cue,” Computer Graphics and Image Processing, vol. 5, pp. 52-67, 1976.
[4] D. Blostein and N. Ahuja,“Representation and three-dimensional interpretation of image texture:An integrated approach,” Proc. Int’l Conf. Computer Vision, pp. 444-449, 1987.
[5] A.C. Bovik,M. Clark,, and W.S. Geisler,“Multichannel texture analysis using localized spatial filters,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, pp. 55-73, 1990.
[6] L. Brown and H. Shvaytser,“Surface orientation from projective foreshortening of isotropic textureautocorrelation,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 510-514, 1988.
[7] H.B. Dwight,Tables of Integrals and Other Mathematical Data, fourth edition, Macmillan, New York, 1961.
[8] D. Gabor,“Theory of communication,” J. Inst. Electrical Engineering, vol. 93, pp. 429-457, 1946.
[9] J. Gårding,Shape from Surface Markings, dissertation, Dept. of Numerical Analysis and Computing Science,Univ. of Stockholm, May 1991.
[10] J. Gårding,“Shape from texture for smooth curved surfaces,” Proc. European Conf. Computer Vision, pp. 630-638, May 1992.
[11] J.P. Havlicek,A.C. Bovik,, and P. Maragos,“Modulation models for image processing and wavelet-based imagedemodulation,” Proc. 26th IEEE Asilomar Conf. Signals, Systems, and Computers, pp. 805-810,Pacific Grove, Calif., Oct. 1992.
[12] B.K. Horn, Robot Vision. Cambridge, Mass.: MIT Press, 1986.
[13] K. Ikeuchi,“Shape from regular patterns,” Artificial Intelligence, vol. 22, pp. 49-75, 1984.
[14] Y.C. Jau and R.T. Chin,“Shape from texture using the Wigner distribution,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 515-523, 1988.
[15] K. Kanatani and T. Chou,“Shape from texture: General principle,” Artificial Intelligence, vol. 38, pp. 1-48, 1989.
[16] J. Kender,“Shape from texture: An aggregation transform that maps a classof textures into surface orientation,” Proc. Sixth Int’l Joint Conf. Artificial Intelligence, pp. 475-480, 1979.
[17] J. Krumm and S.A. Shafer,“Local spatial frequency analysis of image texture,” Third Int’l Conf. Computer Vision, pp. 354-358, Dec. 1990.
[18] J. Krumm and S.A. Shafer,“Shape from periodic texture using the spectrogram,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 284-289,Champaign, Ill., June 1992.
[19] J. Malik and R. Rosenholtz, “A Differential Method for Computing Local Shape-from-Texture for Planar and Curved Surfaces,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 267-273, 1993.
[20] Y. Ohta,K. Maenobu,, and T. Sakai,“Obtaining surface orientation from texels under perspective projection,” Proc. Seventh Int’l Joint Conf. Artificial Intelligence, pp. 746-751, 1981.
[21] O. Rioul and M. Vitterli, "Wavelets and Signal Processing," IEEE Signal Processing Magazine, vol. 8, pp. 14-38, 1991.
[22] K. A. Stevens,“The information content of texture gradients,” Biological Cybernetics, vol. 42, pp. 95-105, 1981.
[23] B.J. Super and A.C. Bovik,“Three-dimensional orientation from texture using gabor wavelets,” Proc. Conf. Visual Communications and Image Processing, SPIE Proc., vol. 1606, Boston, Nov. 1991.
[24] B.J. Super and A.C. Bovik,“Shape-from-texture by wavelet-based measurement of local spectral moments,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 296-301,Champaign, Ill., June 1992.
[25] B.J. Super,“Filters for directly detecting surface orientation in an image,” Proc. Conf. Visual Communications and Image Processing, SPIE Proc., vol. 1818, Boston, Nov. 1992.
[26] B.J. Super,A.C. Bovik,, and W.S. Geisler,“A model of shape from texture using second-order moments of localspatial-frequency spectra,” Annual Meeting Assoc. Research Vision and Ophthalmology,Sarasota, Fla., May 1993.
[27] B.J. Super and A.C. Bovik,“Shape from texture using local spectral moments,” Technical Report TR-93-001, Center Vision and Image Sciences, Univ. of Texas at Austin, Sept. 1993.
[28] A.P. Witkin,“Recovering surface shape and orientation from texture,” Artificial Intelligence, vol. 17, pp. 17-45, 1981.

Index Terms:
Shape from texture, shape recovery, surface orientation, moments, wavelet, spatial frequency, Gabor functions, texture, projection.
Boaz J. Super, Alan C. Bovik, "Shape from Texture Using Local Spectral Moments," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 4, pp. 333-343, April 1995, doi:10.1109/34.385983
Usage of this product signifies your acceptance of the Terms of Use.