Signatures in Shape Analysis: an Efficient Approach to Motion Identification
Differential Geometry
2020-01-15 v1 Computer Vision and Pattern Recognition
Machine Learning
Abstract
Signatures provide a succinct description of certain features of paths in a reparametrization invariant way. We propose a method for classifying shapes based on signatures, and compare it to current approaches based on the SRV transform and dynamic programming.
Cite
@article{arxiv.1906.06406,
title = {Signatures in Shape Analysis: an Efficient Approach to Motion Identification},
author = {Elena Celledoni and Pål Erik Lystad and Nikolas Tapia},
journal= {arXiv preprint arXiv:1906.06406},
year = {2020}
}
Comments
7 pages, 3 figures. Conference paper for Geometric Science of Information 2019