Experimental assessment of the informativity of signs in the analysis of 2d images of bone objects in forensic examination.
https://doi.org/10.21122/2309-4923-2022-3-22-27
Abstract
This article describes the software implementation of the system for extracting and evaluating information features from 2D images of bone fractures and bone objects for classifying fractures and identifying the alleged instrument that caused the injury. As parameters, the textural characteristics of Haralick, local binary patterns of pixels for 2D images, Gabor filters, Laws energy texture characteristics for 2D images 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 bone 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
A. A. Doudkin
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
Doudkin Aleksandr, Doctor of Sciences and Professor of computer science. Head of the Systems Identification Laboratory
Minsk
A. A. Voronov
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
PhD, Associate Professor
Minsk
V. V. Ganchenko
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
PhD
Minsk
E. E. Marushko
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Minsk
Belarus
Minsk
L. P. Podenok
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Minsk
Belarus
Minsk
A. V. Inyutin
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Minsk
Belarus
Minsk
References
1. Volegov, P. S. Povrezhdennost’ i razrushenie: obzor jeksperimental’nyh rabot / P.S. Volegov, D.S.Gribov, P.V. Trusov // Fizicheskaja mezomehanika. – 2015. – T.18. – №3. – S.11–24.. [In russian]
2. Razrushenie. T. 1: Mikroskopicheskie i makroskopicheskie osnovy mehaniki razrushenija / Pod red. G. Libovica. – M.: Mir, 1973. – 620 s. [In russian]
3. Feichtinger, Hans G. Gabor analysis and algorithms : theory and applications./ Feichtinger, Hans G. and Thomas Strohmer. 1998. – Boston: Birkhäuser – 496 p.
4. Laws, K. Rapid texture identifi / Kenneth I. Laws // Proc. SPIE 0238. Image Processing for Missile Guidance. – 1980. – San Diego, USA. – Vol. 238. – PP. 376-381.
5. Haralick, R. M. Textural features for image classifi / R.M. Haralick, K. Shanmugam, I.H. Dinstein // IEEE Trans. on systems, man, and cybernetics, 1973. – № 6. – P. 610–621.
6. Ojala, T. Multiresolution gray-scale and rotation invariant texture classifi with local binary patterns / T. Ojala, M. Pietikainen, T. Maenpaa // IEEE Trans. on pattern analysis and machine intelligence, 2002. – Vol. 24. № 7. – P. 971–987.
7. Nasledov, D. Matematicheskie metody psihologicheskogo issledovanija / D. Nasledov. – 2008. – SPb.: Rech’, 2008. – 172 s. [In russian]
8. Kuhn, M. Applied Predictive Modeling / Kuhn Max and Kjell Johnson. – 2018. – New York, NY: Springer. – 600 P.
9. Support vector clustering/ Ben-Hur, Asa [et al.] // Journal of Machine Learning Research. – 2001. – Vol. 2. – P. 125–137.
10. Geurts, P. Extremely randomized trees / P. Geurts, D. Ernst. and L. Wehenkel // Machine Learning. – 2006. – Vol.63. – P.3-42.
11. Breiman, L. Random Forests / Breiman Leo // Machine Learning, 2001. – Vol.45. – P. 5-32.
Review
For citations:
Doudkin A.A., Voronov A.A., Ganchenko V.V., Marushko E.E., Podenok L.P., Inyutin A.V. Experimental assessment of the informativity of signs in the analysis of 2d images of bone objects in forensic examination. «System analysis and applied information science». 2022;(3):22-27. (In Russ.) https://doi.org/10.21122/2309-4923-2022-3-22-27
Views:
274
Email this article 