PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Adamer, M.F.* ; de Brouwer, E.* ; O’Bray, L.* ; Rieck, B.

The magnitude vector of images.

J. Appl. Comput. Topol., DOI: 10.1007/s41468-024-00182-9 (2024)
Publ. Version/Full Text DOI
Open Access Hybrid
Creative Commons Lizenzvertrag
The magnitude of a finite metric space has recently emerged as a novel invariant quantity, allowing to measure the effective size of a metric space. Despite encouraging first results demonstrating the descriptive abilities of the magnitude, such as being able to detect the boundary of a metric space, the potential use cases of magnitude remain under-explored. In this work, we investigate the properties of the magnitude on images, an important data modality in many machine learning applications. By endowing each individual image with its own metric space, we are able to define the concept of magnitude on images and analyse the individual contribution of each pixel with the magnitude vector. In particular, we theoretically show that the previously known properties of boundary detection translate to edge detection abilities in images. Furthermore, we demonstrate practical use cases of magnitude for machine learning applications and propose a novel magnitude model that consists of a computationally efficient magnitude computation and a learnable metric. By doing so, we address one computational hurdle that used to make magnitude impractical for many applications and open the way for the adoption of magnitude in machine learning research.
Impact Factor
Scopus SNIP
Altmetric
0.000
1.846
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Journal article
Document type Scientific Article
Keywords Computer Vision ; Edge Detection ; Metric Learning ; Metric Space Magnitude
Language english
Publication Year 2024
HGF-reported in Year 2024
ISSN (print) / ISBN 2367-1726
e-ISSN 2367-1734
Journal Journal of Applied and Computational Topology
Publisher Springer
Reviewing status Peer reviewed
Institute(s) Institute of AI for Health (AIH)
POF-Topic(s) 30205 - Bioengineering and Digital Health
Research field(s) Enabling and Novel Technologies
PSP Element(s) G-540003-001
DOI 10.1007/s41468-024-00182-9
Scopus ID 85197411343
Erfassungsdatum 2024-07-18
[➜Report correction]