基于边缘链长度的边缘检测方法

Bound of Step-Structure Edge Detection Approach Based on Length of Edge

在小波图像边缘检测过程中,算法通常是用一个阈值将弱边缘去掉,将奇异性较大的边缘保留。用双阈值取代单阈值可以更好的改善边缘的效果。但双阈值在边缘检测中不好平衡阈值选取中噪声和有效边缘的矛盾,在阈值选取中为了减少噪声的干扰,一些奇异性较弱而长度较长的边缘也被滤掉了,在实际问题中影响了边缘图像的效果。针对这一问题在双阈值算法的基础上得到了基于边缘链长度的边缘检测方法,得到了更好的边缘效果。

It is used to remove weakly edeg with the method of threshold values in the method of wavelet transform ,big and singular edge are reserved. If you use double-threshold values,you could get more good effect. But double-threshold values method isn’t solved well between how to get more valueable edge and how to delet noise,in order to reduce noise ,some weakly but length edge may delet if can’t get proper threshold value double-threshold values. To solve this problem,The new edge detection method based on the double-threshold values is given in this paper. It use the length of edge,good effect is achieved in the image edge detection of the bound of step-structure.