Experimental analysis of harmonic shape images

Authors:
Dongmei Zhang;Martial Hebert
Affiliations:
The Robotics Institute, Carnegie Mellon University;The Robotics Institute, Carnegie Mellon University
Venue:
3DIM'99 Proceedings of the 2nd international conference on 3-D digital imaging and modeling
Year:
1999

Citing 12
Cited 6

The representation, recognition, and locating of 3-d objects

International Journal of Robotics Research
Structural Indexing: Efficient 3-D Object Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
A Method for Registration of 3-D Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Object modelling by registration of multiple range images

Image and Vision Computing - Special issue: range image understanding
Describing Complicated Objects by Implicit Polynomials

IEEE Transactions on Pattern Analysis and Machine Intelligence
Building 3-D models from unregistered range images

Graphical Models and Image Processing
Geometry of harmonic maps

Geometry of harmonic maps
COSMOS-A Representation Scheme for 3D Free-Form Objects

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Spherical Representation for Recognition of Free-Form Surfaces

IEEE Transactions on Pattern Analysis and Machine Intelligence
Triangles as a Primary Representation

Proceedings of the International NSF-ARPA Workshop on Object Representation in Computer Vision
Multi-Scale Classification of 3-D Objects

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
On 3D Shape Similarity

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)

Robust Point Correspondence Applied to Two-and Three-Dimensional Image Registration

IEEE Transactions on Pattern Analysis and Machine Intelligence
High-Quality Texture Reconstruction from Multiple Scans

IEEE Transactions on Visualization and Computer Graphics
Efficient partial-surface registration for 3D objects

Computer Vision and Image Understanding
Registration of partially overlapping surfaces by rejection of false point correspondences

Pattern Recognition
Efficient partial-surface registration for 3D objects

Computer Vision and Image Understanding
Automatic registration for 3D shapes using hybrid dimensionality-reduction shape descriptions

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In our early work, a representation called Harmonic Shape Images for 3D free-form surfaces was proposed and applied to solve the surface-matching problem. In this paper, extensive experiments using real data are conducted to analyze the performance of Harmonic Shape Images with respect to discriminability, stability and robustness to resolution and occlusion. The results show that Harmonic Shape Images are an appropriate representation for 3D surface comparison. Examples of surface comparison using real data are presented in the paper.