数学形态学在空间格局图像骨架提取中的应用

Application of Mathematical Morphology in the Skeleton Extraction of Spatial Pattern Image

本文从遥感图像上提取空间格局的过程中 ,对基于数学形态学的主要细化算法进行了归纳总结 ,结合各算法实现的效果图 ,将其进行对比分析 ,找出它们各自的优缺点。最后对其进行了综合改进 ,针对空间格局图像的复杂多变、非细长的面状特征 ,提出一种提炼其骨架的细化算法 ,并且给出了具体的程序实现方法。

Mathematical morphology is a powerful implement in the research of image analysis.It has been a primary domain of image science and its theory and method has been applied in many fields.The article is to study its method in the process of extracting the skeleton of spatial pattern based on remote sensing data.Spatial pattern image differs from area with slab-sided shape such as character and fingerprint.It is not slab-sided with daedal orientation.The authors sum up the current major mathematical morphology arithmetic of thinning at first.They find out the merits and demerits by analysing the difference between these arithmetic using the resultant contrastive photos.Finally, based on these arithmetic, the authors bring forward an improved arithmetic of skeleton extraction of spatial pattern image that is very fit for not slender bar with large area, furthermore offer the realization method for the program.