Title :
Robust Color Texture Features Under Varying Illumination Conditions
Author :
Kandaswamy, Umasankar ; Adjeroh, Donald A. ; Schuckers, Stephanie ; Hanbury, Allan
Author_Institution :
Dept. of Electr. & Comput. Eng., Lawrence Technol. Univ., Southfield, MI, USA
Abstract :
Under varying illumination, both the statistical and structural contents of color texture are modified, leading to changes in the observed texture surface. We model the effect of illumination as a perturbation on an ideal color texture and show that the spectra of the ambient light have a significant impact on the observed texture patterns in the individual color channels. Motivated by studies in human color constancy, we propose a correlation-based transformation that minimizes the effect of illumination variation in color texture analysis. Experimental results are included, which validate the performance of the proposed minvariance model in the analysis of color texture.
Keywords :
correlation methods; feature extraction; image colour analysis; image texture; statistical analysis; ambient light spectra; color channels; color texture analysis; correlation-based transformation; human color constancy; minvariance model; robust color texture features; statistical contents; structural contents; varying illumination conditions; Color; Correlation; Humans; Image color analysis; Image edge detection; Lighting; Surface texture; Color texture classification; illumination invariants; minvariance model; Algorithms; Color; Colorimetry; Computer Simulation; Image Interpretation, Computer-Assisted; Lighting; Models, Theoretical;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/TSMCB.2011.2162400