基于并行灰度级差共生矩阵的图像纹理检测

Image texture detection based on parallel gray level grade co-occurrence matrix

针对图像纹理检测存在的问题,提出了并行灰度级差共生矩阵方法。首先确定图像灰度级的分布,获得灰度差相关信息作为划分类别的依据;再通过灰度-梯度计算图像灰度值的变化速率;最后确定通道的处理进程与检测像素互联映射,多通道的并行处理事件概率是各单通道联合概率数据互联事件的乘积。实验结果表明,本方法对纹理检测效果清晰。

Aiming at the problems existing in the image texture detection,it is put forward a new method of Parallel Gray Level Grade Co-Occurrence Matrix.At first it is needed to determine the image grayscale distribution and to obtain the difference of information as separate categories;then through gray level-gradient co-occurrence matrix,it is calculated the change rate of the image grayscale.At last the channel process is decided and the pixel interconnected mapping test is made.Multichannel parallel process is the multiplication of single channel probability data of interconnection events.Experimental result shows this texture detection method is effective.