SIFT and Preserving Topology Structures of Local Neighborhood: Matching Feature Point in Deformation Measurement of Nonrigid Biological Tissues from Magnetic Resonance Images
点击次数：
发布时间：2020-05-30
发表刊物：Journal of Medical Imaging And Health Informatics
关键字：EATURE POINT; IMAGE; MATCHING; NONRIGID; SPTSLN
摘要：In this paper, we propose an integrated method SPTSLN (SIFT and Preserving Topology Structures of Local Neighborhood) for feature point matching in MR images of nonlinear and nonuniform deformation of nonrigid tissues. First, from the template and deformed images, the DoG detector and SIFT descriptor are used to extract and describe the feature points. Then the matching probability matrix of relaxation labeling is initialized according to the SIFT matching results of the feature points between the template and deformed images. Subsequently, the relaxation labeling is adopted to update the prob
合写作者：Jia Chen, Xubing Zhang，Yuanquan Xu, Chengxin Ran
通讯作者：张绪冰
是否译文：否