Recovering Surface Curvature and Orientation From Texture Distortion: A Least Squares Algorithm and Sensitivity Analysis

Shape from texture is best analyzed in two stages, analogous to stereopsis and structure from motion: (a) Computing the ‘texture distortion’, and (b) Interpreting the ‘texture distortion’ to infer the orientation and shape of the surface. We model the texture distortion for a given point and direction on the image plane as an affine transformation and derive the relationship between the parameters of this transformation and the shape parameters. We use non-linear minimization of a least squares error criterion to estimate the shape parameters from the affine transformations, using a simple linear algorithm to obtain an initial guess. Under the assumption that the measurement errors in the affine parameters are independent and normally distributed, we can find error bounds on the shape parameter estimates. We present results on images of planar and curved surfaces under perspective projection. We find all five local shape and orientation parameters with no a priori assumptions about the shape of the surface.

[1]  Ruzena Bajcsy,et al.  Texture gradient as a depth cue , 1976 .

[2]  Katsushi Ikeuchi,et al.  Shape from Regular Patterns , 1984, Artif. Intell..

[3]  B. O'neill.  Elementary Differential Geometry , 1966 .

[4]  Jitendra Malik,et al.  A differential method for computing local shape-from-texture for planar and curved surfaces , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Andrew P. Witkin,et al.  Recovering Surface Shape and Orientation from Texture , 1981, Artif. Intell..

[6]  Stanley M. Dunn,et al.  Efficient Recovery of Shape from Texture , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Alan C. Bovik,et al.  Shape-from-texture by wavelet-based measurement of local spectral moments , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Andrew Blake,et al.  Shape from texture: Ideal observers and human psychophysics , 1993, Vision Research.

[9]  Kenichi Kanatani,et al.  Shape from Texture: General Principle , 1989, Artif. Intell..

[10]  Lisa M. Brown,et al.  Surface Orientation from Projective Foreshortening of Isotropic Texture Autocorrelation , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  J. Aloimonos.  Shape from texture , 1988, Biological cybernetics.

[12]  John Krumm,et al.  Shape from periodic texture using the spectrogram , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Andrew Blake,et al.  Shape from texture: the homogeneity hypothesis , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[14]  Andrew Blake,et al.  Shape from Texture: Estimation, Isotropy and Moments , 1990, Artif. Intell..