A.G. Tashlinskii – Dr. Sc. (Eng.), Professor, Head of Department «Radio Engineering», 

Ulyanovsk State Technical University E-mail: tag@ulstu.ru

R.G. Magdeev – Engineer of Communication, OJSC «Ulyanovskneft» E-mail: radiktkd2@yandex.ru

A method for finding the microstructural parameters of low-carbon steel from its metallographic images which makes it possible to determine: the ratio of perlite to ferrite phases, the parameters of grains of crystallites and their mutual arrangement; the degree of granularity of the pearlite phases is proposed. The method is aimed at predicting the strength characteristics of steel samples and consists of several stages. The preprocessing step involves color reduction, refinement of the area of interest, noise filtering, illumination refinement and histogram equalization. The segmentation of the image is associated with the search for the size, area and convex shell of grains. The stage of finding the microstructural parameters is based on the identification stochastic gradient-based estimation of the parameters of the segmented objects. Examples of analysis of samples of steel oil pipelines are given.

1. Arzamasov B.V., Makarova V.I., Muxin G.G., Ry'zhov N.M., Silaeva V.I. Materialovedenie: Uchebnik dlya vuzov / Pod obshh red. B.N. Arzamasova, G.G. Muxina. M.: Izd-vo MGTU im. N.E'. Baumana. 2008. 648 s.
2. Starodubov D.N. Metody' i algoritmy' obrabotki i analiza defektoskopicheskix i metallograficheskix snimkov. Dis. … kand. texn. nauk: 05.13.01. Vladimir. 2008. 183 s.
3. Vinogradova L.A., Magdeev R.G., Kurganova Yu.V. Algoritm opredeleniya sootnosheniya form faz v perlite trubny'x stalej so strukturoj ferrit i perlit // RVM. 2012. № 6. S. 41−45.
4. Vinogradov A.I., Trajno A.I., Sary'cheva I.A. K voprosu o transformaczii zernennoj struktury' metalla pri plasticheskom deformirovanii // Metally'. 2009. № 2. S. 54−60.
5. Tret'yakov A.V., Trofimov G.K., Gur'yanova M.K. Mexanicheskie svojstva stalej i splavov pri plasticheskom deformirovanii. Karmanny'j spravochnik. M.: Mashinostroenie. 1971. 63 s.
6. Vizil'ter Yu.V., Zheltov S.Yu., Bondarenko A.V., Osokov M.V., Morzhin A.V. Obrabotka i analiz izobrazhenij v zadachax mashinnogo zreniya: Kurs lekczij i prakticheskix zanyatij. M.: Fizmatkniga. 2010. 672 s.
7. Baatz M., Schäpe A. Multiresolution Segmentation: an optimization approach for high quality multi-scale image segmentation // Journal of Photogrammetry and Remote Sensing. 2004. V. 58. № 3−4. P. 239−258.
8. Magdeev R.G., Tashlinskij A.G. E'ffektivnost' identifikaczii ob''ektov na binarny'x izobrazheniyax s ispol'zovaniem proczedur psevdogradientnoj adaptaczii // Radiotexnika. 2014. № 7. S. 96−102.
9. Magdeev R.G., Biktimirov L.Sh. Primenenie algoritmov postroeniya vy'pukloj obolochki pri analize izobrazhenij mikrostruktury' metalla // Izvestiya Samarskogo nauchnogo czentra Rossijskoj akademii nauk. 2014. T. 16. № 6(2). S. 496−500.
10. Kormen T., Lejzerson Ch., Rivest R., Shtajn K. Algoritmy'. Postroenie i analiz. Izd. 3-e. M.: Vil'yams. 2013. 1324 s.
11. Barber C.B., Dobkin D.P., Huhdanpaa H. The quickhull algorithm for convex hulls // ACM Transactions on Mathematical Software. 1996. V. 22(4). P. 469−483. DOI: 10.1145/235815.
12. Tashlinskij A.G. Oczenivanie parametrov prostranstvenny'x deformaczij posledovatel'nostej izobrazhenij / Ul'yanovsk: UlGTU. 2000. 132 s.
13. Tashlinskii A.G. Pseudogradient Estimation of Digital Images Interframe Geometrical Deformations / Vision Systems: Segmentation & Pattern Recognition. 2007. Vienna. Austria: I Tech Education and Publishing. P. 465−494. DOI: 10.5772/4975.
14. Magdeev R.G., Tashlinskii A.G. A comparative analysis of the efficiency of the stochastic gradient approach to the identification of objects in binary images // Pattern recognition and image analysis. 2014. V. 24. № 4. P. 535−541. DOI: 10.1134/S1054661814040130.