基于中值-游程共生矩阵的纹理特征提取

Image Texture Segmentation Based on Median-run Length Co-occurrence Matrix

提出了一种基于中值-游程共生矩阵模型的纹理特征提取方法。该方法利用了图像的灰度信息和等灰度游程长度信息,通过计算图像的中值矩阵和游程矩阵,从而计算出中值-游程共生矩阵,来提取图像的特征。仿真结果表明,该方法能有效地分割出纹理图像上区域特性不同的纹理,且分割效果优于等灰度游程矩阵和灰度共生矩阵。

This paper introduced a texture features extracted .algorithm based on median-run length matrix. This method attempted to utilize the information of both gray level and equi-level run-length in an image. In this approach, the median-run length co-occurrence matrix was calculated through evaluating median matrix and run-length matrix, and then used as texture features for segmenting the textures. Experimental results showed that it could effectively segment texture images which had different local detail structures, and its precision of classification was superior to that of the gray-level co-occurrence matrix and gray level-gradient co-occurrence matrix.