Segmentation of Lath-Like Structures via Localized Identification of Directionality in a Complex-Phase Steel
- PDF / 2,719,255 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 78 Downloads / 172 Views
TECHNICAL ARTICLE
Segmentation of Lath‑Like Structures via Localized Identification of Directionality in a Complex‑Phase Steel Martin Müller1,2 · Gerd Stanke3 · Ulrich Sonntag3 · Dominik Britz1,2 · Frank Mücklich1,2 Received: 28 May 2020 / Revised: 14 August 2020 / Accepted: 28 August 2020 © The Author(s) 2020
Abstract In this work, a segmentation approach based on analyzing local orientations and directions in an image, in order to distinguish lath-like from granular structures, is presented. It is based on common image processing operations. A window of appropriate size slides over the image, and the gradient direction and its magnitude inside this window are determined for each pixel. The histogram of all possible directions yields the main direction and its directionality. These two parameters enable the extraction of window positions which represent lath-like structures, and procedures to join these positions are developed. The usability of this approach is demonstrated by distinguishing lath-like bainite from granular bainite in socalled complex-phase steels, a segmentation task for which automated procedures are not yet reported. The segmentation results are in accordance with the regions recognized by human experts. The approach’s main advantages are its use on small sets of images, the easy access to the segmentation process and therefore a targeted adjustment of parameters to achieve the best possible segmentation result. Thus, it is distinct from segmentation using deep learning which is becoming more and more popular and is a promising solution for complex segmentation tasks, but requires large image sets for training and is difficult to interpret. Keywords Microstructure · Segmentation · Local orientation and direction analysis · Region growing · Steel · Bainite
Introduction In material science and especially in the steel industry, rudimentary methods are still frequently used for segmentation, primarily threshold segmentation. However, when analyzing more complex microstructures in steel, traditional segmentation methods have their limitations. For example, bainitic structures, such as granular, upper or lower bainite, are difficult to segment because they differ only in the forms and arrangements of bainitic ferrite and the carbon-rich second phase, but not in their grayscale values. Thus, threshold segmentation cannot be used to separate different bainitic structures. Bainite is an essential constituent of modern * Martin Müller martin.mueller1@uni‑saarland.de 1
Chair of Functional Materials, Saarland University, Saarbrücken, Germany
2
Material Engineering Center Saarland, Saarbrücken, Germany
3
Society for the Advancement of Applied Computer Science, Berlin, Germany
high-strength steels, combining high strength and high toughness, making it interesting for many applications [1]. Despite many years of steel research, bainite is still a controversial topic. Its characterization is challenging because of the variety and number of involved phases as well as the fineness and complexit
Data Loading...
