期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
卷号：5
期号：3
页码：3432
DOI：10.15680/IJIRSET.2016.0503129
出版社：S&S Publications
摘要：Distinctive features are crucial to many tasks in computer assisted minimally invasive surgeries (MIS).Most existing methods are difficult to extract distinctive features in MIS images. For better analysis of MIS images,resort to blood vessels that are abundant and distinctive on the tissue surfaces. In our paper, based on vascularbranching points, propose a new type of vascular feature, branching segment. For special conditions in an MIS imagingenvironment, such as specular reflections and texture homogeneous areas, the feature points extracted by generalfeature point detectors are less distinctive and repeatable in MIS images. Abundant blood vessels are available on tissuesurfaces and can be extracted as a new set of image features. Here two types of blood vessel features are proposed forendoscopic images: branching points and branching segments. Two novel methods, Ridgeness-Based Circle Test andRidgeness-Based Branching Segment Detection are presented to extract branching points and branching segments,respectively.
