SIMILARITY BETWEEN RANDOM SETS CONSISTING OF MANY COMPONENTS

Random sets play an essential role in modelling several phenomena in biology, medicine and material science. However, sometimes it is hard to describe them using a specific model. Therefore it can also be difficult to classify them or to compare their realisations. This contribution proposes a simil...

Full description

Saved in:
Bibliographic Details
Published inImage analysis & stereology Vol. 38; no. 2; pp. 185 - 199
Main Author Gotovac, Vesna
Format Journal Article
LanguageEnglish
Published Slovenian Society for Stereology and Quantitative Image Analysis 01.01.2019
Subjects
kernel test
non-parametric statistics
random tessellation
similarity measure
Online AccessGet full text

Cover

More Information
Summary:Random sets play an essential role in modelling several phenomena in biology, medicine and material science. However, sometimes it is hard to describe them using a specific model. Therefore it can also be difficult to classify them or to compare their realisations. This contribution proposes a similarity measure between two random sets whose realisations consist of many components based on just one realisation of each of them. The similarity measure is obtained in a non-parametric way taking into account the shapes and the positions of the components. The procedure is justified by a simulation study and consequently applied to real biomedical data of histological images of mammary tissue.
ISSN:1580-3139
1854-5165
DOI:10.5566/ias.2017