首页 | 本学科首页   官方微博 | 高级检索  
     

WaterBalloonsSnake模型的数字图像轮廓提取算法
引用本文:罗小刚,黄茜,彭承琳,刘婷,尹鹏,文利,高云华. WaterBalloonsSnake模型的数字图像轮廓提取算法[J]. 重庆大学学报(自然科学版), 2009, 32(1): 116-120
作者姓名:罗小刚  黄茜  彭承琳  刘婷  尹鹏  文利  高云华
作者单位:罗小刚,黄茜,彭承琳,刘婷,尹鹏,LUO Xiao-gang,HUANG Qian,PEN Cheng-lin,LIU Ting,YIN Peng(重庆大学医学电子及仪器研究所,重庆,400030);文利,高云华,WEN Li,GAO Yun-hua(第三军医大学附属新桥医院,重庆,400037)  
摘    要:为解决数字图像如左心室MRI图像存在着弱边缘、与周围组织之间的低对比度区域的特点,传统的Snake模型算法分割数字图像,出现变形曲线泄漏现象这一问题,提出一种改进的Balloons Snake模型-Water Balloons Snake图像分割算法.该算法利用数学形态学理论自动获取左心室数字MRI图像的重心以及边界形状变化允许空间,采用分水岭变换算法获取图像轮廓内壁分水岭线,并以此作为Snake数字模型的初始样条曲线进行进一步轮廓捕获.以小香猪左室加标记MRI数字医学图像作为应用研究对象,对比了几种模型的不同处理结果.实验表明WaterBalloons Snake模型算法比经典Snake模型或Balloons Snake模型算法能够更有效地处理变形曲线泄漏问题,并且具有较快的收敛速度.

关 键 词:Balloon Snake模型算法  分水岭算法  数字图像处理  图像分割

A contour extraction algorithm for digital images based on water balloons snake model
LUO Xiao-gang,HUANG Qian,PEN Cheng-lin,LIU Ting,YIN Peng,WEN Li,GAO Yun-hua. A contour extraction algorithm for digital images based on water balloons snake model[J]. Journal of Chongqing University(Natural Science Edition), 2009, 32(1): 116-120
Authors:LUO Xiao-gang  HUANG Qian  PEN Cheng-lin  LIU Ting  YIN Peng  WEN Li  GAO Yun-hua
Affiliation:1.The Research Institute of Electronics and Medical Instruments;Chongqing University;Chongqing 400030;P.R.China;2.Xinqiao Hospital of the Third Military Medical University;Chongqing 400037;P.R.China
Abstract:Due to weak edges and low contrast areas in digital images,such as a left ventricle in Magnetic Resonance Imaging(MRI) images,a deformation curve may leak from the outer boundary when images are segmented using the traditional snake model.An improved algorithm based on the water balloons snake model is introduced to solve this problem.Firstly,the barycenter and the boundary shape area of the left ventricle in a digital MRI image are obtained through mathematical morphology.The left ventricular watershed lin...
Keywords:balloon snake model algorithm  watershed algorithm  digital image processing  image segmentation  
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《重庆大学学报(自然科学版)》浏览原始摘要信息
点击此处可从《重庆大学学报(自然科学版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号