摘要： 针对传统的基于形态学边缘检测算法抗噪能力较差以及易丢失边缘细节的问题，提出一种自适应的抗噪型边缘检测算法。该算法采用多尺度的结构元素进行滤波，根据边缘方向自动选择相应方向的结构元素进行边缘检测以得到更多的边缘细节。实验结果表明，该算法不仅抗噪能力较强，检测到的边缘细节较多，而且还能提高边缘检测效率，是一种有效的边缘检测算法。

关键词: 边缘检测, 数学形态学, 多尺度, 结构元素

Abstract: The traditional edge detection algorithm based on morphology is poor in antinoise and detecting the details of the edge. In order to solve the problem, this paper proposes an adaptive antinoise edge detection algorithm based on morphology. The algorithm uses multiscale structural elements to remove noise, and then automatically selects the appropriate direction structural elements according to the direction of the edge to get more details of the edge. Experimental results show that the algorithm not only is a strong in antinoise, and can detect more edge details, but also is effective in improving the efficiency of the edge detection, so it is an effective edge detection algorithm.

Key words: edge detection, mathematical morphology, multipledimensioned, structural element

中图分类号: 

• TP391.41