基于欧氏距离及向量内积的骨架提取算法

对骨架算法进行研究,提出一种骨架提取算法.通过对图像内部像素点进行距离变换得到其最近边界点的位置,将内部像素点到最近边界点的向量定义为边界向量,根据物体内部相邻边界向量的方向,计算每个像素点的内积值和其8邻域的最小内积值,得到的最小内积点,以确定的阈值从最小内积点中选取骨架种子点,再对骨架种子点进行处理,得到连通的骨架.试验证明这种算法能保证骨架具的完整性和连通性,正确反映物体的拓扑结构.

A Euclidean Distance and Inner Production Based on Skeleton Extraction

In this paper,a skeleton calculation method is proposed.Distance transform is used to determine the nearest edge element for each pixel in a binary image.A vector from each pixel that stops at the nearest edge element is defined as edge vector.An inner-product for a pixel is calculated as the minimal value of the inner-products of edge vectors of the pixel and its 8 neighbor pixels.Seeds of the skeleton are determined by a threshold for the inner-product value.A well connected skeleton is obtained by growing calculation.It is demonstrated that the proposed algorithm produces a integrated and well connected skeleton that represents object＇s topology.