Shape from texture: an aggregation transform that maps a class of textures into surface orientation

Authors:
John R. Kender
Affiliations:
Department of Computer Science, Carnegie-Mellon University, Pittsburgh, PA
Venue:
IJCAI'79 Proceedings of the 6th international joint conference on Artificial intelligence - Volume 1
Year:
1979

Citing 0
Cited 3

Curvature Estimation Using Shape-from-Texture

Proceedings of the Joint IAPR International Workshops on Advances in Pattern Recognition
Analysis of Curved Textured Surfaces Using Local Spectral Distortion

ICAPR '01 Proceedings of the Second International Conference on Advances in Pattern Recognition
Obtaining a 3-D orientation of projective textures using a morphological method

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new approach to obtaining shape information from textural information in static monocular Images la outlined. Also presented is a new aggregation transform which determines (under certain condition) vanishing points and lines. A theorem is proved which relates this Hough-l0ike transform to the gradient space, showing that the transform also directly indicates local surface orientation. Additionally, the transform is shown to have many properties that make it an appealling substitute for some other current image transforms. An example is given of its application to a synthetic textured Image.