欢迎访问《图学学报》 分享到:

图学学报

• 图像处理与模式识别 • 上一篇    下一篇

多阈值选取与边缘连接的边缘检测算法

  

  • 出版日期:2012-04-27 发布日期:2015-07-28

An edge detection algorithm with multi-threshold selection and edge connection

  • Online:2012-04-27 Published:2015-07-28

摘要: 论文针对Kirsch 边缘检测算子的缺点,提出一种多阈值选取与改进的边
缘连接算法相结合的方法,对图像,尤其是医学图像进行边缘检测。该方法首先用高斯滤波
器对原始图像去噪,使用传统Kirsch 算子计算梯度,然后设定低阈值和自适应阈值来保护
图像弱边缘和提取真正边缘,最后通过改进的边缘连接算法连接边缘。实验结果表明,论文
的方法具有保持弱边缘、连接性好的边缘检测效果。

关键词: 边缘检测, Kirsch 算子, 多阈值选取, 边缘连接

Abstract: For improving Kirsch operator, this paper presents an edge detection algorithm
with multi-threshold selection and edge connection, which is used to detect the edge of images,
especially medical images. The method first denoises the original image by Gaussian filter and
calculates the gradient with the traditional Kirsch operator, then sets a lower threshold and
adaptive thresholds to protect the weak edge and pick up the true edge, and finally detects the
disconnected edge of the image by use of the modified edge connection algorithm. The
experiment results show the efficiency of this method.

Key words: edge detection, Kirsch operator, multi-threshold selection, edge connection