采用自相关和协方差函数在光照—欧氏变化条件下识别彩色纹理(英文)

ILLUMINATION-EUCLIDEAN INVARIANT RECOGNITION OF COLOR TEXTURE USING CORRELATION AND COVARIANCE FUNCTIONS

采用完整的Zernike矩自相关函数集合提取彩色纹理的空间结构信息 .该函数集合生成基于自相关矩的矩阵 ,并在此基础上获得彩色纹理的光照不变因子 .对于不同的光照变化 ,所获矩阵间存在着线性变化关系 .6 0 0幅不同光照和旋转条件下的彩色纹理图像将先前提出的彩色协方差函数与循环和非循环自相关函数进行比较 。

A complete set of Zernike moment correlation functions is used to capture spatial structure of a color texture. The set of moment correlation functions is grouped into moment correlation matrices to be used in illumination invariant recognition of color texture. For any change in the illumination, the moment correlation matrices are related by a linear transformation. Comparisons between suggested color covariance functions with circular and non-circular correlations have been carried out using about 600 textured images in different illuminations and rotations conditions. Our suggested method can promise in high computation efficiency as well as recognition accuracy.