【作者】 李悦； 柏正尧； 刘阳； 郭渊；

【Author】 Li Yue Bai Zhengyao Liu yan Guo yuan (School of Information science and engineering,Yunnan University,Kunming 650091,China)

【机构】 云南大学信息学院；

【摘要】 Beamlet 变换是一种新的图像多尺度分析方法,特别适合于提取图像中的线性特征。Beamlet 是一个在一定范围内的位置、方向和尺度下二进组织的线段库,具有分级、多尺度的特性。本文讨论了 Beamlet 图像分析的基本框架,研究了 Beamlet 变换的实现方法,将 Beamlet 变换应用于 SAR 图像中的道路边缘检测,取得了较好的实验结果。更多还原

【Abstract】 Beametlet transform is a new method of multiscale image analysis.It is especially suited to the line detection in the images.Beamlets are a special dyadically organized collection of line segments,exhibi- ting a range of lengths,positions and orientations.The framework of Beamlet analysis has been described and its implication has been studied in this paper.It is applied to edge detection of the roads in the SAR im- age and the experimental results show the effectiveness of this approach.更多还原