Multi-scale local features based on anisotropic heat difusion and global eigen-structure  

作　　者：LI Shuai QIN Hong HAO AiMin 

机构地区：[1]State Key Laboratory of Virtual Reality Technology and Systems, Beihang University [2]School of Biological Science and Medical Engineering, Beihang University [3]Department of Computer Science, State University of New York at Stony Brook,Stony Brook, NY 11794-4400, USA

出　　处：《Science China(Information Sciences)》2013年第11期53-62,共10页中国科学（信息科学）（英文版）

基　　金：supported in part by National Natural Science Foundation of China(Grant Nos.61190120,61190121,61190125);National Science Foundation of USA(Grant Nos.IIS-0949467,IIS-1047715,IIS1049448)

摘　　要：Multi-scale local feature detection enables downstream registration and recognition tasks in med- ical image analysis. This paper articulates a novel robust method for multi-scale local feature extraction on volumetric data. The central idea is the elegant unification of local/global eigen-structures within the powerful framework of anisotropic heat diffusion. First, the local vector field is constructed by way of Hessian matrix and its eigenvectors/eigenvalues. Second, anisotropic heat kernels are computed using the vector field＇s global graph Laplacian. Robust local features are manifested as extrema across multiple time scales, serving as volumetric heat kernel signature. To tackle the computational challenge for massive volumetric data, we propose a multi- resolution strategy for hierarchical feature extraction based on our feature-preserving down-sampling approach. As a result, heat kernels and local feature identification can be approximated at a coarser level first, and then are pinpointed in a localized region at a finer resolution. Another novelty of this work lies at the initial heat design directly using local eigenvalue for anisotropic heat diffusion across the volumetric domain. We conduct experiments on various medical datasets, and draw comparisons with 3D SIFT method. The diffusion property of our local features, which can be interpreted as random walks in statistics, makes our method robust to noise, and gives rise to intrinsic multi-scale characteristics.Multi-scale local feature detection enables downstream registration and recognition tasks in med- ical image analysis. This paper articulates a novel robust method for multi-scale local feature extraction on volumetric data. The central idea is the elegant unification of local/global eigen-structures within the powerful framework of anisotropic heat diffusion. First, the local vector field is constructed by way of Hessian matrix and its eigenvectors/eigenvalues. Second, anisotropic heat kernels are computed using the vector field＇s global graph Laplacian. Robust local features are manifested as extrema across multiple time scales, serving as volumetric heat kernel signature. To tackle the computational challenge for massive volumetric data, we propose a multi- resolution strategy for hierarchical feature extraction based on our feature-preserving down-sampling approach. As a result, heat kernels and local feature identification can be approximated at a coarser level first, and then are pinpointed in a localized region at a finer resolution. Another novelty of this work lies at the initial heat design directly using local eigenvalue for anisotropic heat diffusion across the volumetric domain. We conduct experiments on various medical datasets, and draw comparisons with 3D SIFT method. The diffusion property of our local features, which can be interpreted as random walks in statistics, makes our method robust to noise, and gives rise to intrinsic multi-scale characteristics.

关 键 词：volumetric heat kernel anisotropic diffusion multi=scale local feature local/global eigen-structure volumetric image 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] X17[自动化与计算机技术—计算机科学与技术]