基于改进的Snake模型分割肝脏的CT图像

Snake（主动轮廓线）模型,具有良好的获取特定区域内目标边缘的能力,是一种极为有效的图像分割方法,利用围绕目标心形的圆环内平均灰度差异来确定初始轮廓点,对噪声的干扰有一定的抑制作用,并减少了人工选取的工作量,将离散Snake算法与分段DP算法有效结合来获取肝脏CT图像的特征边缘点,以提高Snake算法的收敛速度。最后利用单调性原则对肝脏CT图像的边缘点进行分区,在各个单调区间内采用曲线拟合的方法来获得连续的肝脏CT图像边缘,最后用Roipoly函数,由这些坐标显示原输入图像,得到BW的二值图像,最终可以显示完整的CT值没有改变的肝脏图像。

CT Images Segmentation of Liver Based on Improved Snake Model

Snake （Active Contour）model has good ability to obtain objective＇s margin of specific region,and is an extremely effective method of image segmentation.It uses average gray-scale differences of the ring around the target to make sure of the initial contour points,and has inhibition effect to the interference of noise,also can reduce the workload of manual selection.Through the discrete Sub-Snake algorithm and effective integration of DP algorithm to obtain CT images of the characteristics of the edge of the liver in order to improve the convergence rate of Snake algorith.Finally,carried on partitioning to the CT edge points of liver using the principle of monotonicity ,and obtained continuous CT images of liver edge using method of curve fitting in each monotone interval.Using roipoly function,original input images are displayed,and BW binary images are abtained.Ultimately,complete liver images of whom the CT value has not changed could be displayed.