结合LOG算子和小波变换的图像边缘检测方法

摘要

This paper studies the causes of noise sensitivity and edge coarseness using usual edge detection presently.A new method for image edge detection based on data fusion is presented,which detects the edge of original image with improved LOG and DWT respectively,then produces a new image by fusing the two results above.Experiment shows that proposed method gath-ers excellence of two detection method,increases veracity effectively and a much better edge detection result.%针对目前常用的边缘检测方法对噪声比较敏感,测得的边缘比较粗糙等现象,在传统边缘检测方法的基础上提出了一种基于数据融合的边缘捡测方法.该方法分别采用改进的LOG算子和离散小波变换对原始图像进行边缘检测,建立相应的融合原则,并将两种方法检测出来的边缘进行数据融合,得到最终的图像边缘.实验证明,该方法结合了两种检测方法的优点,有效地提高了边缘检测准确性,获得了比较理想的边缘检测效果.