HKSD for deformation measurement of nonrigid biological tissues from MR images
Jia Chen, Ruhan He, Xubing Zhang, Jun Bai · 2017
Due to the nonlinear deformation of nonrigid and nonuniform tissues, it is challenging to accurately measure the displacements of feature points distributed on the inner parts, boundaries, and separatrices of tissue layers.To address this challenge, we propose a feature point matching technique called HKSD to measure MR 2-D slice deformation of nonuniform and nonrigid biological tissues.Finally, we describe patches based on the Heat Kernel Signature (HKS).We apply Gaussian function as weigh to noise 2D image.The experimental results showed that the proposed HKSD method outperformed the single SURF and SIFT methods.