Content Based X-ray Image Analysis of Aluminium Castings

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27360%2F11%3A86080839" target="_blank" >RIV/61989100:27360/11:86080839 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1504/IJCMSSE.2011.042820" target="_blank" >http://dx.doi.org/10.1504/IJCMSSE.2011.042820</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1504/IJCMSSE.2011.042820" target="_blank" >10.1504/IJCMSSE.2011.042820</a>

Result language

angličtina

Original language name

Content Based X-ray Image Analysis of Aluminium Castings

Original language description

The X-ray digital images of aluminium castings containing different microstructure defects were characterized by feature vectors composed from i) first-order statistics, ii) singular values and iii) second-order statistics calculated from Grey Level Co-occurrence Matrices (GLCM). The most suitable features were found by means of the Ward?s clustering method. The X-ray images characterised by the first-order statistics, such as 1st to 6th statistical moments and entropy, were portioned in 2 main clusterswith efficiency of 90 %. Consequently, using the 6 statistical moments and entropy, aluminium castings were sorted according to their quality in comparison with one casting of no observable defects. Their similarity was expressed measured by the Euclidean distance (ED). At ED = 5 the quality aluminium castings were effectively separated from the defective ones. This image analysis approach can be simply implemented into the automatic quality control of metallurgical processes and could

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JG - Metallurgy, metal materials

OECD FORD branch

—

Project

<a href="/en/project/ED0040%2F01%2F01" target="_blank" >ED0040/01/01: Regional materials science and technology centre</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2011

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

International Journal Computational Materials Science and Surface Engineering

ISSN

1753-3465

e-ISSN

—

Volume of the periodical

4

Issue of the periodical within the volume

3

Country of publishing house

CH - SWITZERLAND

Number of pages

13

Pages from-to

219-231

UT code for WoS article

—

EID of the result in the Scopus database

—