Shape from Texture from a Multi-Scale Perspective
Tony Lindeberg and Jonas GardingTechnical report CVAP116: ISRN KTH/NA/P--93/03--SE.
Shortened version in Proc. 4th International Conference on Computer Vision, (Berlin, Germany), 683--691, May 1993.
AbstractThe problem of scale in shape from texture is addressed. The need for (at least) two scale parameters is emphasized; a local scale describing the amount of smoothing used for suppressing noise and irrelevant details when computing primitive texture descriptors from image data, and an integration scale describing the size of the region in space over which the statistics of the local descriptors is accumulated.
A novel mechanism for automatic scale selection is used, based on normalized derivatives. It is used for adaptive determination of the two scale parameters in a multi-scale texture descriptor, the windowed second moment matrix, which is defined in terms of Gaussian smoothing, first order derivatives, and non-linear pointwise combinations of these. The same scale-selection method can be used for multi-scale blob detection without any tuning parameters or thresholding.
The resulting texture description can be combined with various assumptions about surface texture in order to estimate local surface orientation. Two specific assumptions, ``weak isotropy'' and ``constant area'', are explored in more detail. Experiments on real and synthetic reference data with known geometry demonstrate the viability of the approach.
Note! Only a shortened version is available here (please contact your library or ask a secretary at our department for the printed long version of this report.
Shortened conference paper: (PDF 0.5Mb)
Related work: (Affine shape adaptation for improving the accuracy of surface orientation estimates) (Shape from disparity gradients using second-moment matrices) (Combined framework for direct computation of shape cues from local image deformations) (Monograph on scale-space theory)
Responsible for this page: Tony Lindeberg