一种改进型多尺度DDCM主动轮廓模型边界检测算法

史耀明; 鲍旭东; 王遵亮

doi:10.11834/jig.20030390

学术论文与技术报告 | 浏览量 : 0 下载量: 187 CSCD: 0

PDF
导出
分享
收藏
专辑

一种改进型多尺度DDCM主动轮廓模型边界检测算法
A Novel Multi-scale Fast Algorithm for Edge Detection Based on DDCM Active Contour Model
2003年8卷第3期页码：256
纸质出版：2003
DOI： 10.11834/jig.20030390
稿件说明：

移动端阅览

史耀明, 鲍旭东, 王遵亮. 一种改进型多尺度DDCM主动轮廓模型边界检测算法[J]. 中国图象图形学报, 2003,8(3):256. DOI： 10.11834/jig.20030390.

A Novel Multi-scale Fast Algorithm for Edge Detection Based on DDCM Active Contour Model[J]. Journal of Image and Graphics, 2003, 8(3): 256. DOI： 10.11834/jig.20030390.

摘要

尽管主动轮廓模型 (Active contour model)，或称 Snakes

近年来已经在计算机视觉和图象处理领域得到了广泛的应用，尤其在边界检测方面也表现出良好的性能，但是由于传统的 Snakes图象边界检测对初始轮廓线的位置十分敏感，因而限制了它的更广泛应用.为了克服这一问题，提出了一种改进型多尺度 DDCM主动轮廓模型的边界检测算法，该算法是首先通过分阶段改变轮廓曲线的内力，使轮廓曲线的曲率能自适应地进行多尺度调整，进而改变了轮廓线的柔性和刚性，使之能够更好地与目标边界匹配.实验结果证明，该算法在计算速度和边界检测精度上，均优于传统的主动轮廓边界检测算法，因而具有一定的实用价值.

Abstract

In the last decade

Active Contour Model(Snakes) has been successfully applied in the areas of computer vision and image processing. In particular

it reveal much potentials for edge detection and tracking. However

traditional Active Contour Models are very sensitive to the position of initial contour

which limits its further application in edge detection area. To overcome this problem

an accurate and fast multi-scale DDCM active contour model is proposed in this paper

where the curvature of the contour is modulated according to different step during edge detection. We employ this approach to detect the edge of interested objects in CT images. Compared with traditional active contour model

the proposed algorithm has a better performance of edge detection with the aspects of accuracy and speed

which is showed by our experiments.