一种改进的双模态图像分割算法

Improved segmentation algorithm for bimodal image

在Mumford-Shah模型基础上提出了一个改进的双模态图像分割算法。该算法基于图像局部化信息创建驱动曲线演化的能量,引入的配准项提高了曲线的演化速度,基于曲线演化竞争的数据拟合项,使得曲线能更稳定地收敛到一个全局静态最小值,且算法对水平集函数初始化位置不敏感。实验结果表明,改进的算法具有收敛速度快、分割结果稳定的特点,尤其在医学CT图像方面具有更强的分割能力,更高的稳定性。

This paper presents a improved segmentation algorithm for bimodal image based on the Mumford-Shah model.The energy which drives the evolution of a curve is constructed based on local image information,the alignment term enhances the speed of curve evolution,and the improved data fitting term which is based on the competition between of the shifted Heaviside functions,makes the curve converge to a better global stationary minimum.The experiments show that the improved algorithm has a faster speed of convergence and a more stable segmentation result,especially has a more powerful ability of segmentation and higher stability in segmentation of medical CT images.