一种多尺度的灰度不均匀图像分割方法

A Multi-Scale Image Segmentation Method for Image with Intensity Inhomogeneity

灰度不均匀是阻碍图像准确分割的一种障碍,在真实图像中灰度不均匀现象经常存在。提出一种多尺度的局部区域型水平集方法,通过设定不同的局部区域,分析各个区域的灰度不均匀和拟合项,然后对其求平均值,再借助水平集方法构建最终的能量泛函。对比实验证明了本文提出方法的有效性,且对于灰度不均匀图像能够得到更准确的分割效果。

It is difficult to accurately segment images with intensity inhomogeneity.However,the phenomenon of intensity inhomogeneity often exists in real images.By setting different local regions and analyzing the intensity inhomogeneity,a multi scale local regional level set method is proposed in this paper.In the proposed method,the each region of image is fitted and then incorporated into a region by solving mean value.The effectiveness of the proposed method is testified by contrast experiments,and it can get more accurate segmentation effects for intensity inhomogeneous image.