摘要
在医学图像分割技术的研究中,针对提取图像的清晰度和快速性问题,常用轮廓跟踪算法来提取组织轮廓线,花费的时间较长且分割效果不好。为了提高组织轮廓线的提取速度和分割效果,利用医学图像中组织对称性和灰度特征,提出了双向轮廓跟踪算法。根据分割目标确定相应的检测阈值,采用边缘检测,确定边缘起始点,对组织边缘进行双向跟踪。在检测过程中,设置相应的检测矩阵,减少检测次数。算法能同时沿两个不同的方向进行边缘检测,节省了时间。仿真结果表明,改进的轮廓提取方法对有较好的连续性和对称性的组织轮廓线能进行快速准确地提取,可得到清晰的分割结果,缩短轮廓线的生成时间。
At present,the contour tracking algorithm is used to segment the tissue contour line.This algorithm is a one-direction tracking.The costed time is long and the segmentation results are not good.In order to improve the segmentation speed and segmentation results,using symmetry of tissues and the grayscale features in medical image,bidirectional contour tracking algorithm is proposed.At first,the detection threshold is specified and detects images with specific threshold.Then specify the edge starting point and track tissue edges with two directions.At last,obtain associated tissue contour lines.In detection process,detection matrix is used to avoid repeated detections and decrease the number of detections.The improved algorithm can detect the contour with two-direction and save the time cost.Experimental results show that the improved contour extraction method can quickly and accurately segment tissue contour lines which have good continuity and symmetry and have clear segmentation results.The time for creating contour lines is shortened.
出处
《计算机仿真》
CSCD
北大核心
2011年第3期271-274,368,共5页
Computer Simulation
关键词
图像分割
灰度值
边缘检测
轮廓跟踪
Image segmentation
Gray value
Edge detection
Contour tracking
