基于各向异性扩散的医学图像分水岭分割算法

Watershed segmentation algorithm for medical image based on anisotropic diffusion filtering

针对医学图像形态建模过程易产生过分割的问题,提出了一种基于各向异性扩散的分水岭分割算法。该算法首先对原始图像进行自适应各向异性扩散滤波,然后引入多尺度的形态梯度图像作为分水岭变换的参考图像,以突出图像中物体的边界轮廓,平滑具有均匀亮度的区域。最后,定义基于边界平均灰度和面积的区域合并准则,对分割后的区域进一步合并。实验结果表明,该算法能有效抑制过分割,具有较强的抗噪声性能,得到的分割结果可以满足医学图像建模的需要。

Although watershed transformation is a powerful tool for image segmentation, it might give rise to oversegmentation. A novel medical image segmentation algorithm based on anisotropic diffusion filtering using watershed transformation was proposed. First, input image was got through adaptive anisotropic diffusion filter, and then, a multi-scale morphological grads image was obtained as the input of watershed so as to give prominence to the contours of the image and smooth the areas with even luminance. Experiments show that the algorithm can restrain the over-segmentation phenomena effectively, thus obtaining good segmentation results.