Author： Seifi Mozhdeh Song Xiaohu Muselet Damien Trémeau Alain
Publisher： Society for Imaging Science and Technology
ISSN： 2158-6330
Source： Conference on Colour in Graphics, Imaging, and Vision, Vol.2010, Iss.1, 2010-01, pp. : 332-337
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
Color has been shown to be a very important clue in the context of texture classification. However, since color is not stable across illumination changes, color invariant descriptors are required when the illumination is not controlled. In this paper, we propose to characterize color textures by analyzing the rank correlation between pixels located in the neighborhood from each other. Thus, considering one distance and one direction in the image space, we obtain a correlation measure which i) is related to the colors of the pixels, ii) is not sensitive to illumination changes, iii) represents the spatial interactions between different color components of neighbored pixels. Furthermore, we show how this measure can be very fast extracted from co-occurrence matrices. The discriminative power of this descriptor is assessed on a public color texture database.
Related content
Access to resources
Recommend
