基于动态梯度向量流的活动轮廓模型  被引量:1

An Improved Active Contour Model Based on Dynamic Gradient Vector Flow

在线阅读下载全文

作  者:张建 吴桂玲 赵喜玲 ZHANG Jian;WU Gui-ling;ZHAO Xi-ling(XinYang College of Agriculture and Forestry,College of Information Engineering,Xinyang464000,Chin)

机构地区:[1]信阳农林学院信息工程学院

出  处:《控制工程》2018年第7期1344-1347,共4页Control Engineering of China

基  金:河南省科技攻关基金资助项目(172102210120)

摘  要:针对传统活动轮廓模型不能准确有复杂边界的难题,提出一种基于动态梯度向量流的活动轮廓模型。首先通过边界指示函数对边缘梯度图进行处理,并扩散形成一个动态力场,然后通过边界停止函数控制轮廓曲线演化,避免出现早期收敛现象,使轮廓曲线向凹形边界收敛,最后进行了仿真测试实验。结果表明,相对于与其他模型,本文模型可以准确分割出长凹形边界,提高了对噪声的鲁棒性。Traditional active contour model on gradient vector flow has problems that the contour curve is difficult to converge to the long concave boundary, so a dynamic gradient vector flow model for is proposed in this paper. Basic principle is to weight processing of edge gradient map using the indicator function, and spread to form a dynamic force field, and then convergence of contour curve is controlled by the boundary stop function to develop the information of the evolving contour curve effectively, which can largely avoid the problem of early convergence, and it can make the contour curve converge to the concave boundary. Compared with the traditional models, the simulation tests show that the proposed model can segment the object of the long concave boundary, and it has a good effect on the boundary complex object.

关 键 词:动态梯度向量流 活动轮廓模型 边界停止函数 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象