Skeleton based shape matching and retrieval

PANORAMA: A 3D Shape Descriptor Based on Panoramic Views for Unsupervised 3D Object Retrieval

“…In [22] Zhang et al consider the use of medial surfaces to compute an equivalent directed acyclic graph of an object. In the work of Sundar et al [23], the 3D object passes through a thinning process producing a set of skeletal points, which finally form a directed acyclic graph by applying the minimum spanning tree algorithm. Cornea et al [24] propose the use of curve skeletons produced by the application of the generalized distance field to the volume of the 3D object and similarity is measured using the earth mover's distance.…”

Local Shape Similarity Retrieval of Mechanical Parts

“…The first step of 3D voxel SIFT is the computation of multi-scale DoG ( Difference of C ): G x y z kσ is the Gaussian function. k is an integer in [1,5] to indicate different levels of scale. σ is a constant that set to 3 2 .…”

“…The similarity between 3D objects can be measured by computing the distance between signatures under a predefined metric. According to the genre of shape information that a signature describes, shape signature can be generally classified as follows: geometry based [1,2,3], topology based [4,5] and feature based [6,7].…”

Efficient 3D shape matching and retrieval using a concrete radialized spherical projection representation

“…In [19] Zhang et al consider the use of medial surfaces to compute an equivalent directed acyclic graph of a voxelized model. Sundar et al [20] also proposed skeleton based shape matching. They first obtain the volume of a 3D model which passes through a thinning process producing a set of skeletal points, which finally form a directed acyclic graph by applying the minimum spanning tree algorithm.…”