Statistical Analysis of Locally Parameterized Shapes

DOI10.1080/10618600.2022.2116445arXiv2109.03027MaRDI QIDQ6094095FDOQ6094095

Authors: Jörn Schulz 

Publication date: 9 October 2023

Published in: Journal of Computational and Graphical Statistics (Search for Journal in Brave)

Abstract: The alignment of shapes has been a crucial step in statistical shape analysis, for example, in calculating mean shape, detecting locational differences between two shape populations, and classification. Procrustes alignment is the most commonly used method and state of the art. In this work, we uncover that alignment might seriously affect the statistical analysis. For example, alignment can induce false shape differences and lead to misleading results and interpretations. We propose a novel hierarchical shape parameterization based on local coordinate systems. The local parameterized shapes are translation and rotation invariant. Thus, the inherent alignment problems from the commonly used global coordinate system for shape representation can be avoided using this parameterization. The new parameterization is also superior for shape deformation and simulation. The method's power is demonstrated on the hypothesis testing of simulated data as well as the left hippocampi of patients with Parkinson's disease and controls.

Full work available at URL: https://arxiv.org/abs/2109.03027

Recommendations

• scientific article; zbMATH DE number 1194132
• The statistical analysis of shape data
• Statistical shape theory
• An invariant approach to statistical analysis of shapes
• DIFFERENTIAL SHAPE STATISTICAL ANALYSIS
• scientific article; zbMATH DE number 778010
• Statistical analysis of shape of objects based on landmark data.
• A survey of the statistical theory of shape

zbMATH Keywords

skeletal representationParkinson's diseaselocal coordinate systemshape alignmentlocal dissimilaritys-rep hypothesis testing

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Functional and shape data analysis
• Title not available (Why is that?)
• Analysis of principal nested spheres
• Title not available (Why is that?)
• Statistical shape analysis. With applications in R
• Statistical decision theory and Bayesian analysis. 2nd ed
• Persistent homology transform for modeling shapes and surfaces
• Title not available (Why is that?)
• Exploring uses of persistent homology for statistical analysis of landmark-based shape data
• Swept regions and surfaces: Modeling and volumetric properties
• Backwards principal component analysis and principal nested relations
• Nested sphere statistics of skeletal models
• Medial representations. Mathematics, algorithms and applications
• Means and Averaging in the Group of Rotations
• Pivotal Bootstrap Methods fork-Sample Problems in Directional Statistics and Shape Analysis
• Metrics for 3D rotations: comparison and analysis
• An invariant approach to statistical analysis of shapes
• Small-sphere distributions for directional data with application to medical imaging
• Kurtosis test of modality for rotationally symmetric distributions on hyperspheres

Cited In (9)

• Directional statistics and shape analysis
• New likelihoods for shape analysis
• Local Statistics on Shape Diffeomorphisms Using a Depth Potential Function
• Title not available (Why is that?)
• DIFFERENTIAL SHAPE STATISTICAL ANALYSIS
• Intuitive, localized analysis of shape variability
• Title not available (Why is that?)
• Statistical analysis on high-dimensional spheres and shape spaces
• Statistical analysis of scale-space

This page was built for publication: Statistical Analysis of Locally Parameterized Shapes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6094095)