K-MEANS CLUSTERING IN TEXTURED IMAGE: EXAMPLE OF LAMELLAR MICROSTRUCTURE IN TITANIUM ALLOYS

This paper presents an implementation of the k-means clustering method, to segment cross sections of X-ray micro tomographic images of lamellar Titanium alloys. It proposes an approach for estimating the optimal number of clusters by analyzing the histogram of the local orientation map of the image...

Full description

Saved in:
Bibliographic Details
Published inInformatyka, automatyka, pomiary w gospodarce i ochronie środowiska Vol. 7; no. 3; pp. 43 - 46
Main Authors Al Darwich, Ranya, Babout, Laurent, Strzecha, Krzysztof
Format Journal Article
LanguageEnglish
Published Lublin University of Technology 01.09.2019
Subjects
k-means clustering
number of clusters
oriented textured
X-ray tomography
Online AccessGet full text

Cover

More Information
Summary:This paper presents an implementation of the k-means clustering method, to segment cross sections of X-ray micro tomographic images of lamellar Titanium alloys. It proposes an approach for estimating the optimal number of clusters by analyzing the histogram of the local orientation map of the image and the choice of the cluster centroids used to initialize k-means. This is compared with the classical method considering random coordinates of the clusters.
ISSN:2083-0157
2391-6761
DOI:10.5604/01.3001.0010.5213