(46-3) 14 * << * >> * Russian * English * Content * All Issues

Determination of fibers volume fraction in layered composite materials by optical methods
V.A. Komarov 1, A.A. Pavlov 1

Samara National Research University, 443086, Samara, Russia, Moskovskoye Shosse 34

 PDF, 1389 kB

DOI: 10.18287/2412-6179-CO-1068

Pages: 473-478.

Full text of article: Russian language.

A problem of determining the fiber volume fraction in fiber-reinforced strands of fabric-based laminated composites is considered. As a source of information about the structure of the material, digital micrographs of the ground surface of the cross-sections of the composites are used. Methods and features of the analysis of raster microscopic images of heterogeneous material associated with variable pixel brightness and blurring of the "fiber-binder" boundaries are discussed. To make the image processing less labor-intensive and more objective, a special autoencoder is proposed and built. The study of the structure of a typical structural carbon fiber-reinforced plastic is illustrated by an end-to-end demonstration example. A significant acceleration of the image processing process using the convolutional autoencoder and a good agreement of the results with a careful manual analysis are shown.

composite, fiber, volume fraction, micrograph, image processing, autoencoder.

Komarov VA, Pavlov AA. Determination of fibers volume fraction in layered composite materials by optical methods. Computer Optics 2022; 46(3): 473-478. DOI: 10.18287/2412-6179-CO-1068.

This work was financially supported by the RF Ministry of Science and Higher Education of the Russian Federation under the project FSSS-2020-0016.


  1. Niu MCY. Composite airframe structures: Practical design information and data. 3rd ed. Granada Hills: Adaso/Adastra Engineering Center; 2000. ISBN: 978-962-7128-06-6.
  2. Lomov S, Ivanov DS, Verpoest I, Zako M. Full-field strain measurements for validation of meso-FE analysis of textile composites. Compos Part A Appl Sci Manuf 2008; 39(8): 1218-1231. DOI: 10.1016/j.compositesa.2007.09.011.
  3. Gommer F, Endruweit A, Long A. Quantification of micro-scale variability in fibre bundles. Compos Part A Appl Sci Manuf 2016; 87: 131-137. DOI: 10.1016/j.compositesa.2016.04.019.
  4. Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 1979; 9(1): 62-66. DOI: 10.1109/tsmc.1979.4310076.
  5. Shi Z, Setlur S, Govindaraju V. Digital image enhancement using normalization techniques and their application to palm leaf manuscripts. 2005. Source: <https://cedar.buffalo.edu/~zshi/Papers/kbcs04_261.pdf>.
  6. Sauvola J, Pietikäinen M. Adaptive document image binarization. Pattern Recognit 2000; 33(2): 225-236. DOI: 10.1016/s0031-3203(99)00055-2.
  7. Su B, Lu S, Tan C. Binarization of historical document images using the local maximum and minimum. Proc 9th IAPR Int Workshop on Document Analysis Systems 2010: 159-165. DOI: 10.1145/1815330.1815351.
  8. Castellanos FJ, Gallego AJ. A selectional auto-encoder approach for document image binarization. Pattern Recognit 2019; 86: 37-47. DOI: 10.1016/j.patcog.2018.08.011.
  9. Pastor-Pellicer J, España-Boquera S, Zamora-Martínez F, Zeshan Afzal M, Castro-Bleda MJ. Insights on the use of convolutional neural networks for document image binarization. In Book: Rojas I, Joya G, Catala A, eds. Advances in Computational Intelligence. Part II. Springer International Publishing; 2015: 115-126. DOI: 10.1007/978-3-319-19222-2_10.
  10. Peng X, Cao H, Natarajan P. Using convolutional encoder-decoder for document image binarization. 14th IAPR Int Conf on Document Analysis and Recognition 2017: 708-713. DOI: 10.1016/j.patcog.2018.08.011.
  11. Rehman A, Saba T. Neural networks for document image preprocessing: State of the art. Artif Intell Rev 2014; 42(2): 253-273. DOI: 10.1007/s10462-012-9337-z.
  12. Bank D, Koenigsteain N, Giryes R. Autoencoders. Source: <https://www.researchgate.net/publication/339945889_Autoencoders>.
  13. About Keras. The Functional API. Source: <https://keras.io/guides/functional_api/>.
  14. About Keras. Keras API reference: Convolution 2D layers. Source: <https://keras.io/api/layers/convolution_layers/convolution2d/>.
  15. Turchenko V, Luczak A. Creation of a deep convolutional auto-encoder in caffe. Source: <https://www.researchgate.net/publication/286302172_Creation_of_a_Deep_Convolutional_Auto-Encoder_in_Caffe>.
  16. About Keras. Keras API reference: MaxPooling2D layer. Source: <https://keras.io/api/layers/pooling_layers/max_pooling2d/>.
  17. About Keras. Keras API reference: UpSampling2D layer. Source: <https://keras.io/api/layers/reshaping_layers/up_sampling2d/>.
  18. About Keras. Keras API reference: Optimizers_Adam. Source: <https://keras.io/api/optimizers/adam/>.
  19. Kingma D, Ba J. Adam: A method for stochastic optimization. Source: <https://www.researchgate.net/publication/269935079_Adam_A_Method_for_Stochastic_Optimization>.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20