K-MEANS CLUSTERING IN TEXTURED IMAGE: EXAMPLE OF LAMELLAR MICROSTRUCTURE IN TITANIUM ALLOYS
Journal Title: Informatyka Automatyka Pomiary w Gospodarce i Ochronie Środowiska - Year 2017, Vol 7, Issue 3
Abstract
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.
Authors and Affiliations
Ranya Al Darwich, Laurent Babout, Krzysztof Strzecha
SIMULATION AND COMPARISON OF SELECTED FAST CHARGER TOPOLOGIES
The article reviews the role of fast chargers in swiftly developing area of electrical energy storage devices. Energy efficient techniques implemented in fast chargers are shown, world standard requirements are mentioned...
WPŁYW TEMPERATURY POŻARU NA WARTOŚĆ NAPIĘCIA ZASILAJĄCEGO URZĄDZENIA ELEKTRYCZNE ORAZ SKUTECZNOŚĆ OCHRONY PRZECIWPORAŻENIOWEJ URZĄDZEŃ, KTÓRE MUSZĄ FUNKCJONOWAĆ W CZASIE POŻARU
Bezpieczeństwo pożarowe jest jednym z najważniejszych wymagań stawianych współczesnym budynkom. Wiąże się z nim szereg wymagań technicznych, które należy spełnić na etapie projektowania. Ponieważ najważniejszym elementem...
THE DEPENDENCE BETWEEN THE NUMBER OF ROUNDS AND IMPLEMENTED NODES IN LEACH ROUTING PROTOCOL-BASED SENSOR NETWORKS
In the 21st century wireless sensor networks have gained much popularity due to their flexibility. This progress has enabled the use of sensor nodes on an unprecedented scale and opened new opportunities for the so-calle...
DISTORTIONLESS SIGNALS TRANSFER THROUGH A WIRE MEDIA METASTRUCTURE
In the paper the development of the components of communication means is considered based on the wire metastructures. This approach is novel and quite promising due to the metamaterials provides new opportunities for the...
FLAME MONITORING USING IMAGE CLASSIFICATION
This paper presents comparison of image classification methods for co-firing biomass and pulverized coal. Two classes of combustion – stable and unstable were defined for nine variants with different power value par...