基于一种新的Snake模型的序列图像边缘提取算法  

Boundary extracting algorithm for image sequence using a novel Snake model

作　　者：马建林[1] 崔志明[1] 张娜敏[2] 吴健[1] 孙晓平[1] 

机构地区：[1]苏州大学智能信息处理及应用研究所,江苏苏州215006 [2]西北工业大学应用数学系,西安710072

出　　处：《计算机应用》2008年第4期982-985,1005,共5页journal of Computer Applications

摘　　要：对医学图像数据中感兴趣区域(ROI)进行准确的边缘提取和分割,是对图像进行分析、理解和处理的重要前提。为克服现有Snake算法人工初始化轮廓不精确,迭代过程中曲线易被复杂背景吸引等缺点,提出基于一种改进Snake模型的序列图像边缘提取算法。该算法先利用序列图像相似性原理提取出近似边缘,然后将其平均分为4个子边缘,在每个子边缘上取数目均衡的Snake输入点,最后离散Snake的内力和外力,经过迭代得到最终边缘。实验结果表明:该方法能精确地提取出医学图像中复杂区域或畸形区域的边缘,且计算量较小。Boundary extraction and segmentation for Region of Interest （ROI） of medical image is an important prerequisite for analyzing, understanding and handling the images. In traditional algorithms, Snake curve initialized manually was inaccurate and easily attracted by the complex background. In order to overcome these shortcomings, a boundary extracting model of image sequence was proposed based on Snake model for medical image sequence with irregular region and complex features. Approximate boundary of image ＇sequence was extracted by using similarity principle, and then the boundary was divided into four sub-boundaries. The sample points in the sub-boundaries keep the points balanced between the sub- boundaries. Lastly, these points were taken as the input of the contour searching in the Snake model, and the inner and external energy functions based on traditional Snake model were improved and dispersed. The experimental results show that the new method could extract boundary of the complex and abnormal regions in medical images, and has great robustness and practicality.

关 键 词：边缘提取 子边缘 SNAKE模型 序列图像 贪婪算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]