Application of texture filtering in clustering of x-ray computed tomography data of products from polymer composite materials

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription Access

Abstract

X-ray computed tomography (XCT) is one of the most informative methods of nondestructive testing of polymer composite materials (PCM) and products made of them. One of the important stages of XCT of PCM products is segmentation, the automation of which is of research interest. In the segmentation process it is important to identify isotexture zones containing local X-ray density variations. In this paper we investigated the possibilities of three-dimensional texture filtering (Gaussian filter, Gabor filters) in clustering of X-ray computed tomography data by simple linear iterative clustering (SLIC) algorithm and evaluated their efficiency in terms of parameters: the share of mismatches between the boundaries of clusters and the boundaries of segmented areas and sphericity of clusters, as well as the performance in terms of time to partition the dataset into the required number of clusters. The results of the study show that the application of three-dimensional texture filters improves the clustering accuracy and sphericity of isotexture clusters of PCM product XCT data without a significant increase in clustering time compared to the raw data. The maximum increase in clustering accuracy was observed when using a combination of Gaussian and Gabor filters, while clustering time increased.

Full Text

Restricted Access

About the authors

Aleksandr V. Shirshin

ITMO University; Federal State Budgetary Military Educational Institution of Higher Education «Kirov Military Medical Academy» of the Ministry of Defence of the Russian Federation

Email: asmdot@gmail.com
ORCID iD: 0000-0002-1494-9626
SPIN-code: 4412-0498
Scopus Author ID: 57809284700
Russian Federation, 197101 Saint Petersburg, Kronverksky avenue, 49 A; 194044 Saint Petersburg, Akademika Lebedeva str., 6 ZH

Aleksey V. Fedorov

ITMO University

Email: afedor62@yandex.ru
ORCID iD: 0000-0003-0612-922X
SPIN-code: 2489-4043
Scopus Author ID: 57219346304
Russian Federation, 197101 Saint Petersburg, Kronverksky avenue, 49 A

Igor S. Zheleznyak

Federal State Budgetary Military Educational Institution of Higher Education «Kirov Military Medical Academy» of the Ministry of Defence of the Russian Federation

Email: igzh@bk.ru
ORCID iD: 0000-0001-7383-512X
SPIN-code: 1450-5053
Scopus Author ID: 57201822052
Russian Federation, 194044 Saint Petersburg, Akademika Lebedeva str., 6 ZH

Stepan A. Peleshok

Federal State Budgetary Military Educational Institution of Higher Education «Kirov Military Medical Academy» of the Ministry of Defence of the Russian Federation

Author for correspondence.
Email: peleshokvma@mail.ru
ORCID iD: 0000-0002-9460-8126
SPIN-code: 3657-9756
Scopus Author ID: 6507481006
Russian Federation, 194044 Saint Petersburg, Akademika Lebedeva str., 6 ZH

References

  1. Dhakate P.D., Chordia S.N. Shape Memory Polymers and Composites in Aerospace Applications // International Journal of Engineering Research. 2020. V. 9. No. 11.
  2. Valueva M.I., Evdokimov A.A., Nacharkina A.V., Gubin A.M. Polymer Composite Materials And Technologies In The Automotive Industry // Proceedings of VIAM. 2022. No. 1. P. 53—65.
  3. Ramakrishna S., Mayer J., Wintermantel E., Leong K.W. Biomedical applications of polymer-composite materials: a review // Composites Science and Technology. 2001. V. 61. Biomedical applications of polymer-composite materials. No. 9. P. 1189—1224.
  4. Pires L., Magalhães F., Moreira Pinto A. New Polymeric Composites Based on Two-Dimensional Nanomaterials for Biomedical Applications // Polymers. 2022. V. 14. P. 1464.
  5. Oladele I., Adelani S., Agbabiaka O., Adegun M. Applications and Disposal of Polymers and Polymer Composites: A Review // Applications and Disposal of Polymers and Polymer Composites. 2022. V. 9. No. 3. P. 65—89.
  6. Chen J., Yu Z., Jin H. Nondestructive testing and evaluation techniques of defects in fiber-reinforced polymer composites: A review // Frontiers in Materials. 2022. V. 9. Nondestructive testing and evaluation techniques of defects in fiber-reinforced polymer composites.
  7. Garcea S.C., Wang Y., Withers P. X-ray computed tomography of polymer composites // Composites Science and Technology. 2017. V. 156.
  8. Straumit I., Lomov S., Wevers M. Quantification of the internal structure and automatic generation of voxel models of textile composites from X-ray computed tomography data // Composites Part A: Applied Science and Manufacturing. 2015. V. 69.
  9. Berg S., Saxena N., Shaik M., Pradhan C. Generation of ground truth images to validate micro-CT image-processing pipelines // The Leading Edge. 2018. V. 37. P. 412—420.
  10. Distante A., Distante C. Handbook of Image Processing and Computer Vision. V. 2. From Image to Pattern / Handbook of Image Processing and Computer Vision. 2020.
  11. Chauhan S., Rühaak W., Khan F., Enzmann F., Mielke P., Kersten M., Sass I. Processing of rock core microtomography images: Using seven different machine learning algorithms // Computers & Geosciences. 2016. V. 86. Processing of rock core microtomography images. P. 120—128.
  12. Taneja A., Ranjan P., Ujjlayan A. A performance study of image segmentation techniques / 2015 4th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO) (Trends and Future Directions). Noida, India: IEEE. 2015. P. 1—6.
  13. Mendoza A., Trullo R., Wielhorski Y. Descriptive Modeling of Textiles using FE Simulations and Deep Learning. Т. 213 // Journal Abbreviation: Composites Science and Technology. 2021.
  14. Sinchuk Y., Kibleur P., Aelterman J., Boone M., Van Paepegem W. Variational and Deep Learning Segmentation of Very-Low-Contrast X-ray Computed Tomography Images of Carbon/Epoxy Woven Composites // Materials. 2020. V. 13. P. 936.
  15. Auenhammer R., Mikkelsen L., Asp L., Blinzler B. Automated X-ray computer tomography segmentation method for finite element analysis of non-crimp fabric reinforced composites // Composite Structures. 2020. V. 256. P. 113136.
  16. Sukemi, Sukrisno E. Identification using the K -Means Clustering and Gray Level Co-occurance Matrix (GLCM) At Maturity Fruit Oil Head / 2019 Fourth International Conference on Informatics and Computing (ICIC) 2019 Fourth International Conference on Informatics and Computing (ICIC). Semarang, Indonesia: IEEE, 2019. P. 1—4.
  17. Zhou B. Image Segmentation Using Slic Superpixels and Affinity Propagation Clustering // International Journal of Science and Researc. 2015. V. 4. No. 4. IJSR. P. 1525—1529.
  18. Lowekamp B., Chen D., Yaniv Z., Yoo T. Scalable Simple Linear Iterative Clustering (SSLIC) Using a Generic and Parallel Approach // The Insight Journal. 2018.
  19. Nowosad J., Stepinski T.F. Extended SLIC superpixels algorithm for applications to non-imagery geospatial rasters // International Journal of Applied Earth Observation and Geoinformation. 2022. V. 112. P. 102935.
  20. Fedorov A., Beichel R., Kalpathy-Cramer J., Finet J., Fillion-Robin J.-C., Pujol S., Bauer C., Jennings D., Fennessy F., Sonka M., Buatti J., Aylward S., Miller J.V., Pieper S., Kikinis R. 3D Slicer as an Image Computing Platform for the Quantitative Imaging Network // Magnetic resonance imaging. 2012. V. 30. No. 9. P. 1323—1341.
  21. Zack G.W., Rogers W.E., Latt S.A. Automatic measurement of sister chromatid exchange frequency // Journal of Histochemistry & Cytochemistry. 1977. V. 25. No. 7. P. 741—753.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. A fragment of the dataset without affine transformation with 12 clusterable repeating combinations of filling parts.

Download (384KB)
Indexing metadata
3. Fig. 2. An example of partitioning into clusters (cluster boundaries are highlighted in yellow) of a data set with an affine transformation (rotation minus 45°).

Download (775KB)
Indexing metadata
4. Fig. 3. Submaximal shares of clusters (grayscale) intersected by reference contours of repeating combinations of filling parts (straight lines).

Download (164KB)
Indexing metadata
5. Fig. 4. Cluster boundaries during clustering without preprocessing (left) and with the use of texture filters (right).

Download (1MB)
Indexing metadata

Copyright (c) 2025 Russian Academy of Sciences