Matching 2D and 3D articulated shapes using the eccentricity transform

► We propose a method for matching 2D and 3D shapes. ► The method builds on the computation of longest geodesic distances in a shape. ► A shape is described by two histograms: one for compactness and one for structure. ► Competitive results are achieved for connected shapes undergoing articulation....

Full description

Saved in:
Bibliographic Details
Published in:Computer vision and image understanding 2011-06, Vol.115 (6), p.817-834
Main Authors: Ion, Adrian, Artner, Nicole M., Peyré, Gabriel, Kropatsch, Walter G., Cohen, Laurent D.
Format: Article
Language:English
Subjects:
Applied sciences
Articulation
Artificial intelligence
Computation
Computer science
control theory
systems
Eccentricity
Eccentricity transform
Exact sciences and technology
Geodesic distance
Histograms
Matching
Pattern recognition. Digital image processing. Computational geometry
Shape matching
Three dimensional
Transforms
Two dimensional
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:► We propose a method for matching 2D and 3D shapes. ► The method builds on the computation of longest geodesic distances in a shape. ► A shape is described by two histograms: one for compactness and one for structure. ► Competitive results are achieved for connected shapes undergoing articulation. This paper presents a novel method for 2D and 3D shape matching that is insensitive to articulation. It uses the eccentricity transform, which is based on the computation of geodesic distances. Geodesic distances computed over a 2D or 3D shape are articulation insensitive. The eccentricity transform considers the length of the longest geodesics. Histograms of the eccentricity transform characterize the compactness of a shape, in a way insensitive to rotation, scaling, and articulation. To characterize the structure of a shape, a histogram of the connected components of the level-sets of the transform is used. These two histograms make up a highly compact descriptor and the resulting method for shape matching is straightforward. Experimental results on established 2D and 3D benchmarks show results similar to more complex state of the art methods, especially when considering articulation. The connection between the geometrical modification of a shape and the corresponding impact on its histogram representation is explained. The influence of the number of bins in the two histograms and the respective importance of each histogram is studied in detail.
ISSN:1077-3142
1090-235X
DOI:10.1016/j.cviu.2011.02.006