Skeleton extraction of cerebral vascular image based on topology node

Skeleton extraction has important application value on object recognition, shape retrieval and feature extraction. Traditional skeleton extraction methods more or less have some flaws. Due to the complexity and diversity of cerebral blood vessels images, the traditional skeleton extraction algorithm can not often get continuous skeletons. This paper presents a new framework to calculate the continuous brain blood vessel skeleton curves of binary images and gray-scale images. Algorithm first determines the shape topology nodes of objects, then extract skeletons using the topology nodes as sources point. Experiment and analysis can verify the validity and robustness of this method and it is not sensitive to the boundary noise. This electronic document is a “live” template. The various components of your paper [title, text, heads, etc.] are already defined on the style sheet, as illustrated by the portions given in this document.