Evaluation of metal objects surface parameters informativity using 2D and 3Ddata For classification of fractures
https://doi.org/10.21122/2309-4923-2021-4-55-60
Abstract
This article describes evaluation the information content of metal objects surfaces for classification of fractures using 2D and 3D data. As parameters, the textural characteristics of Haralick, local binary patterns of pixels for 2D images, macrogeometric descriptors of metal objects digitized by a 3D scanner are considered. The analysis carried out on basis of information content estimation to select the features that are most suitable for solving the problem of metals fractures classification. The results will be used for development of methods for complex forensic examination of complex polygonal surfaces of solid objects for automated system for analyzing digital images.
About the Authors
V. A. Ganchenko
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Minsk
Belarus
Minsk
E. E. Marushko
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
Minsk
L. P. Podenok
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
Minsk
A. V. Inyutin
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
Minsk
References
1. Goodremont E. Special steels. – M .: Metallurgy, 1966. – 1274 p. [In russian]
2. Yezhov, A.A. Defects in metals. Directory-atlas / A.A. Ezhov, L. P. Gerasimova – Moscow: Russian University, 2002. – 360 p. [In russian].
3. Fractodiagnostics of destruction of metallic materials and structures / G. V. Klevtsov et al. – M .: MISiS, 2007. – 264 p. [In russian].
4. Ways and methods of increasing reliability and durability of mechanical engineering and instrument-making products: collection / under the editorship of BM Bobkov, M. Yu. Katsnelson, 1968. – 809 p. [In russian].
5. Haralick, R. M. Textural features for image classification / R. M. Haralick, K. Shanmugam, I. H. Dinstein // IEEE Transactions on systems, man, and cybernetics, 1973. – № 6. – P. 610–621.
6. Ojala, T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns / T. Ojala, M. Pietikainen, T. Maenpaa // IEEE Transactions on pattern analysis and machine intelligence, 2002. – Vol. 24. № 7. – P. 971–987.
7. To develop algorithms for automated classification of digitized data of fracture surface macro-relief obtained by the Artec Space Spider scanner. To develop experimental software for studying macrogeometric parameters of fractures based on results of scanning using the Artec Space Spider scanner [Text]: research report (final) / OIPI NAS of Belarus; hands. Dudkin A.A. – Minsk, 2020. [In russian].
Review
For citations:
Ganchenko V.A., Marushko E.E., Podenok L.P., Inyutin A.V. Evaluation of metal objects surface parameters informativity using 2D and 3Ddata For classification of fractures. «System analysis and applied information science». 2021;(4):55-60. (In Russ.) https://doi.org/10.21122/2309-4923-2021-4-55-60
Views:
422
Email this article 