基于形态学和小波的遥感图像边缘检测

A new approach to edge detection based on morphology and wavelet toward applications on remote sense image processing

针对遥感图像噪声含量大、边缘细节丰富等特点,提出了一种基于形态学和小波分析相结合的遥感图像边缘检测方法,即利用小波变换将遥感图像分解为低频和高频两部分分别进行处理,低频采用形态学锐化算法改善低频边缘清晰度后构造全方位多结构元素进行形态学边缘检测,高频引入小波阈值去噪算法进行预处理后利用小波模极大值进行边缘检测,最后进行边缘图像融合。实验结果表明:该方法在有效抑制噪声的同时,实现了边缘的精确定位,细节提取效果好。

To satisfy the specialty of remote sense image such as strong noise and large numbers of edge details,a new approach combinig wavelet with morphology of edge detection is proposed for the remote sense image processing. First by wavelet transform,it decomposes the original image to high frequency part and low frequency part,which are handled independently. After improvement of the low frequen-cy edge definition by using the arithmetic of morphology edge sharpening,the omnidirectional morphological elements a...