Boundary detection using an improved active contour model without edges

被引：0

作者：

Xia, Haiying ^{[1
,2
,3
]}

Yan, Yuanhui ^{[1
]}

Huang, Siqi ^{[1
]}

Xiao, Wenjing ^{[1
]}

机构：

[1] College of Electronic Engineering, Guangxi Normal University, Guilin , China

[2] Guangxi Key Laboratory of Automatic Detecting Technology and Instruments, Guilin , China

[3] Key Laboratory for the Chemistry and Molecular Engineering of Medicinal Resources (Guangxi Normal University), Ministry of Education of China, Guilin , China

来源：

Journal of Computational Information Systems | 2014年 / 10卷 / 24期

关键词：

Edge detection - Image enhancement;

D O I：

10.12733/jcis12630

中图分类号：

O24 [计算数学];

学科分类号：

070102 ;

摘要：

In this paper, we propose an improved active contour without edges to detect boundary in a given image, based on the techniques of curve evolution, gradient vector flow and snakes. Our improved model will stop on the desired boundary under the double constraints in the gradient and a particular image segmentation. We minimize an energy, which contains two types of external energy, to search the best boundary. The stopping term not only depends on the gradient of the images, but also relates to a particular image segmentation. The weights between the external gradient energy and the other gradient from a particular image segmentation can be determined adaptively. The proposed method is operated on various images for evaluating the performance of our method. The experiment results demonstrate that our method can obtain better boundary, compared to ACWE (Active Contour without Edges) algorithm, the traditional snake (TS) and GVF-snake algorithm.

引用

页码：10603 / 10609