基于云模型的图像阈值分割方法

Image Threshold Segmentation Based on Cloud Model

针对图像阈值分割中的最优阈值选择问题,提出一种基于云模型选择最优阈值的图像分割方法。该方法首先利用云变换对图像进行处理,生成原子云模型作为泛概念树的叶结点,通过概念跃升得到基于云模型的图像泛概念树,得出最优阈值初步划分图像的背景和目标,运用极大判定法得到图像分割结果。实验结果表明,该方法的分割效果较好,是一种有效的图像分割方法。

An image thresholding method is proposed to select the optimal threshold for image threshold segmentation.First,an image is transformed to atomic cloud models as the leaf node of the pan-concept-tree by cloud transformation.An image pan-con⁃ceptual-tree based on cloud model can be obtained by concept jump.And then,the optimal threshold can be derived to divide the background and target of the image.Finally,the result of image segmentation is obtained by maximum determination method.It is indicated by experiments that the proposed method yields accurate and robust result,and it is an effective image segmentation meth⁃od.