一种基于snake模型的边缘轮廓提取的改进算法  

A Improved Algorithms of Contours Extraction Brink Based on the Snake

作　　者：谢锋[1] 沈军[1] 满家巨[1] 

机构地区：[1]湖南师范大学数学与计算机科学学院,湖南长沙410081

出　　处：《湖南文理学院学报（自然科学版）》2007年第1期75-77,共3页Journal of Hunan University of Arts and Science(Science and Technology)

基　　金：湖南教育厅青年项目(04013)

摘　　要：snake模型的引入是近代数字图象处理领域的一次革新,该模型对计算机视觉产生了重大影响并受到了广泛的关注,但由于snake模型本身存在许多不足,尤其是全局最小能量的欠稳定性和收敛速度缓慢等问题,使得snake模型的应用受到一定制约.本文提出了一种基于snake模型的边缘轮廓提取的改进算法,该算法主要采用对目标轮廓的中心坐标进行跟踪,同时保持原封闭图象的相关特性,并利用轮廓中心坐标和目标轮廓的相互关系,更快更准确地实现对目标轮廓的迭代,从而加快用sanke模型实现轮廓提取的速度.It is an innovated area for introducing snake models to modem, digital image processing, in addition, the model of computer vision has been widespread concerned, However, there are many snake model which is inadequate, especially for its less common minimum energy stability and the slow pace of convergence, which was limited on the application. The improvement algorithm of snake model based on the brink contours extractions, is used to tracking the center coordinates of target contours, while maintaining the original closed images related characteristics by using relationship between the center coordinates and outline the contours of the objectives. In this way, the rate of contours extraction is greatly accelerated.

关 键 词：SNAKE模型 轮廓提取 动态轮廓 

分 类 号：TP211.52[自动化与计算机技术—检测技术与自动化装置]