skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Use of invariants for recognition of three-dimensional color textures

Abstract

We introduce an image model for color texture based on spatial correlation functions defined both within and between color bands. We show that three-dimensional geometric transformations of a surface in the scene produce corresponding transformations in these correlation functions. From this analysis we derive invariants of color correlation functions that can be computed efficiently and that can be used for geometry-invariant recognition. We show experimentally that these invariants are effective for recognition in situations in which neither color distributions nor gray-scale texture is sufficient. After recognition the estimated color correlation functions can be used to recover the three-dimensional location and orientation of surfaces. The color-texture invariants can be used in the recognition of three-dimensional objects, the segmentation of images of three-dimensional scenes, and the searching of image data bases.

Authors:
;  [1]
  1. Department of Electrical and Computer Engineering, University of California, Irvine, California 92717 (United States)
Publication Date:
Sponsoring Org.:
USDOE
OSTI Identifier:
165008
Resource Type:
Journal Article
Journal Name:
Journal of the Optical Society of America, Part A: Optics and Image Science
Additional Journal Information:
Journal Volume: 11; Journal Issue: 11; Other Information: PBD: Nov 1994
Country of Publication:
United States
Language:
English
Subject:
66 PHYSICS; COLOR; IMAGES; DISTRIBUTION; SURFACES; ROUGHNESS; ALGORITHMS; CAMERAS

Citation Formats

Kondepudy, R, and Healey, G. Use of invariants for recognition of three-dimensional color textures. United States: N. p., 1994. Web. doi:10.1364/JOSAA.11.003037.
Kondepudy, R, & Healey, G. Use of invariants for recognition of three-dimensional color textures. United States. https://doi.org/10.1364/JOSAA.11.003037
Kondepudy, R, and Healey, G. Tue . "Use of invariants for recognition of three-dimensional color textures". United States. https://doi.org/10.1364/JOSAA.11.003037.
@article{osti_165008,
title = {Use of invariants for recognition of three-dimensional color textures},
author = {Kondepudy, R and Healey, G},
abstractNote = {We introduce an image model for color texture based on spatial correlation functions defined both within and between color bands. We show that three-dimensional geometric transformations of a surface in the scene produce corresponding transformations in these correlation functions. From this analysis we derive invariants of color correlation functions that can be computed efficiently and that can be used for geometry-invariant recognition. We show experimentally that these invariants are effective for recognition in situations in which neither color distributions nor gray-scale texture is sufficient. After recognition the estimated color correlation functions can be used to recover the three-dimensional location and orientation of surfaces. The color-texture invariants can be used in the recognition of three-dimensional objects, the segmentation of images of three-dimensional scenes, and the searching of image data bases.},
doi = {10.1364/JOSAA.11.003037},
url = {https://www.osti.gov/biblio/165008}, journal = {Journal of the Optical Society of America, Part A: Optics and Image Science},
number = 11,
volume = 11,
place = {United States},
year = {1994},
month = {11}
}