Title :
Surface orientation from projective foreshortening of isotropic texture autocorrelation
Author :
Brown, Lisa Gottesfeld ; Shvaytser, Haim
Author_Institution :
Dept. of Comput. Sci., Columbia Univ., New York, NY, USA
Abstract :
A method for determining local surface orientation from the autocorrelation function of statistically isotropic textures is introduced. It relies on the foreshortening that occurs in the image of an oriented surface, and the analogous foreshortening produced in the texture autocorrelation function. This method assumes textural isotropy, but does not require the texture to be composed of texels or assume texture regularities such as equal-area texels or equal spacing between texels. This technique is applied to natural images of planar textured surfaces and found to give good results in many instances. The simplicity of the method and its use of information from all parts of the image are emphasized
Keywords :
pattern recognition; picture processing; isotropic texture autocorrelation; local surface orientation; pattern recognition; picture processing; projective foreshortening; Autocorrelation; Computer science; Computer vision; Gradient methods; Histograms; Image reconstruction; Layout; Surface fitting; Surface reconstruction; Surface texture;
Conference_Titel :
Computer Vision and Pattern Recognition, 1988. Proceedings CVPR '88., Computer Society Conference on
Conference_Location :
Ann Arbor, MI
Print_ISBN :
0-8186-0862-5
DOI :
10.1109/CVPR.1988.196283