This paper proposed a new model for measuring the texture periodicity and similarity based on the variogram of geostatistics.
本文基于空间统计学提出了新的纹理周期性和相似性度量。
The paper suggests an approach, utilizing the weighted polynomial regression for the best fitting of the variogram about spherical model or two-order nested spherical model.
本文提出了一种用加权多项式回归对球状模型和二级套合球状模型的变差函数进行最优拟合的方法。
The variogram value and the variable distance calculated by the variogram function are used for the segmentation of texture image. This method is proved to be feasible and effective by experiments.
文中算法根据变差函数的这种性质将单步长变差函数值作为图像纹理特征进行分割,实验结果表明它对纹理图像分割与识别是十分有效的。
应用推荐