Open AccessK-MEANS CLUSTERING IN TEXTURED IMAGE: EXAMPLE OF LAMELLAR MICROSTRUCTURE IN TITANIUM ALLOYS
Author(s) -
R. Al Darwich,
Laurent Babout,
K. Strzecha
Publication year - 2017
Publication title -
informatyka, automatyka, pomiary w gospodarce i ochronie środowiska
Language(s) - English
Resource type - Journals
eISSN - 2391-6761
pISSN - 2083-0157
DOI - 10.5604/01.3001.0010.5213
Subject(s) - centroid , lamellar structure , histogram , cluster analysis , cluster (spacecraft) , image (mathematics) , titanium , microstructure , materials science , titanium alloy , orientation (vector space) , artificial intelligence , computer science , pattern recognition (psychology) , mathematics , metallurgy , geometry , alloy , programming language
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.