Automated Grain Counting for the Microstructure of Mg Alloys Using an Image Processing Method

Akkoyun F., Ercetin A.

JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE, vol.31, no.4, pp.2870-2877, 2022 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 31 Issue: 4
  • Publication Date: 2022
  • Doi Number: 10.1007/s11665-021-06436-2
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, PASCAL, Aerospace Database, Applied Science & Technology Source, Aquatic Science & Fisheries Abstracts (ASFA), Chemical Abstracts Core, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Metadex, Civil Engineering Abstracts
  • Page Numbers: pp.2870-2877
  • Keywords: automated counting, computer vision, grain size, microstructure, OpenCV, powder metallurgy, TENSILE PROPERTIES, SIZE, AL
  • Karadeniz Technical University Affiliated: No


In this study, a practical and swift approach for calculating the number of grains in a microstructure and determining the ASTM grain size of Mg alloys was demonstrated using computer vision technology. In the experiments, Mg alloys were used as work materials. Microscopic images were taken by scanning electron microscopy (SEM) and were subjected to the image processing method. The grains in the microstructure were counted by the image processing method and manually. The experimental results were examined by comparing the manual and automated grain counting results. The standard deviation of the grain numbers was found to be 6% between the manual and automated counting methods. The success rate in the comparison of the grain numbers is approximately 94%. Moreover, ASTM grain sizes were calculated according to the number of grains determined in the SEM images, and a high success rate was achieved by equalizing the ASTM grain sizes of each alloy according to both methods.