Global spectral graph wavelet signature for surface analysis of carpal bones

TL;DR

This paper introduces a spectral graph wavelet method for analyzing the shape of carpal bones, providing an efficient, isometry-invariant global descriptor that improves shape comparison across populations.

Contribution

The paper proposes a novel global spectral graph wavelet signature for surface analysis, with an efficient aggregation method that enhances shape comparison accuracy and reduces memory usage.

Findings

Outperforms recent GPS embedding approaches in shape comparison

Efficient global descriptor with isometry invariance

Validated on a public dataset of carpal bones from 20 individuals

Abstract

In this paper, we present a spectral graph wavelet approach for shape analysis of carpal bones of human wrist. We apply a metric called global spectral graph wavelet signature for representation of cortical surface of the carpal bone based on eigensystem of Laplace-Beltrami operator. Furthermore, we propose a heuristic and efficient way of aggregating local descriptors of a carpal bone surface to global descriptor. The resultant global descriptor is not only isometric invariant, but also much more efficient and requires less memory storage. We perform experiments on shape of the carpal bones of ten women and ten men from a publicly-available database. Experimental results show the excellency of the proposed GSGW compared to recent proposed GPS embedding approach for comparing shapes of the carpal bones across populations.