This Article 
 Bibliographic References 
 Add to: 
Adaptive Scale Filtering: A General Method for Obtaining Shape From Texture
July 1995 (vol. 17 no. 7)
pp. 713-718

Abstract—We introduce adaptive scale filtering, a general method for deriving shape from texture under perspective projection without recourse to prior segmentation of the image into geometric texture elements (texels), and without thresholding of filtered images.

If texels on a given surface can be identified in an image then the orientation of that surface can be obtained [11]. However, there is no general characterization of texels for arbitrary textures. Furthermore, even if the size and shape of texels on the surface is invariant with regard to position, perspective projection ensures that the size and shape of the corresponding image texels vary by orders of magnitude.

Commencing with an initial set F0 of identical image filters, adaptive scale filtering iteratively derives a set FN which contains a unique filter for each image position. Each element of FN is tuned to the three-dimensional structure of the surface; that is, all image filters in FN back-project to an identical shape and size on the surface. Thus image texels of various sizes, but associated with a single spatial scale on the surface, can be identified in different parts of the image. When combined with conventional shape from texture methods, edges derived using FN provide accurate estimates of surface orientation. Results for planar surfaces are presented.

[1] J. Aloimonos,“Shape from texture,” Biological Cybernetics, vol. 58, pp. 345-360, 1988.
[2] R. Bajcsy and L. Lieberman,“Texture gradients as a depth cue,” Computer Graphics and Image Processing, pp. 52-67, 1976.
[3] A. Blake and C. Marinos,“Shape from texture: Estimation, isotropy and moments,” Artificial Intelligence, vol. 45, pp. 323-380, 1990.
[4] D. Blostein and N. Ahuja, “Shape From Texture: Integrating Texture-Element Extraction and Surface Estimation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 12, pp. 1233-1251, Dec. 1989.
[5] J. Gårding,“Shape from surface markings,” PhD thesis, Department of Numerical Analysis and Computing Science, University of Stockholm, Sweden, 1991.
[6] J.Y. Jau and R.T. Chin, “Shape from Texture Using Wigner Distribution,” Computer Vision, Graphics, and Image Processing,” vol. 52, pp. 248-263, 1990.
[7] A. Johnston,“The geometry of the striate topographic map: Functional implications,” Models of Brain Function, R.M.J. Cotterill, Ed. Cambridge: Cambridge University Press, 1989.
[8] K. Kanatani and T. Chou,“Shape from texture: General principle,” Artificial Intelligence, vol. 38, pp. 1-48, 1989.
[9] P. Kube,“Using frequency and orientation tuned channels to determine surface slant,” Eighth Ann. Conf. Cognitive Society, pp. 235-244,Amherst, Mass., 1986.
[10] D. Marr,Vision.San Francisco: WH Freeman, 1981.
[11] Y. Ohta,K. Maenobu, and T. Sakai,“Obtaining surface orientation from texels under perspective projection,” Proc. Seventh IJCAI,Vancouver, Canada, pp. 746-751, 1981.
[12] J.V. Stone,“Shape from texture: Textural invariance and the problem of scale in perspective images of textured surfaces,” Proc. British Machine Vision Conf.,Oxford, England, pp. 181-187, 1990.
[13] J.V. Stone,“Shape from texture: A computational analysis,” PhD thesis, Experimental Psychology, University of Sussex, England, 1991 (also published as Technical Report 209, Cognitive and Computing Sciences, University of Sussex, 1991 ).
[14] J.V. Stone,“The adaptive bisector method: Separating slant and tilt in estimating shape from texture,” Proc. British Machine Vision Conf.,Leeds, England, pp. 177-186, 1992.
[15] J.V. Stone,“Shape from local and global analysis of texture,” Philosophical Trans. Royal Society London, Series B, pp. 53-65, 339:1287, Jan. 1992.
[16] M.R. Turner,G.L. Gerstein, and R. Bacjsy,“Underestimation of visual texture slant by human observers: a model,” Biological Cybernetics, vol. 65, pp. 215-226, 1991.
[17] A.P. Witkin,“Recovering surface shape and orientation from texture,” Artificial Intelligence, vol. 17, pp. 17-45, 1981.

Index Terms:
Shape from texture, filter, adaptive, scale perspective.
J.v. Stone, S.d. Isard, "Adaptive Scale Filtering: A General Method for Obtaining Shape From Texture," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 7, pp. 713-718, July 1995, doi:10.1109/34.391414
Usage of this product signifies your acceptance of the Terms of Use.