Segmentation of Lath-Like Structures via Localized Identification of Directionality in a Complex-Phase Steel

• Published in: Metallography, microstructure, and analysis Vol. 9; no. 5; pp. 709 - 720
• Main Authors: Müller, Martin, Stanke, Gerd, Sonntag, Ulrich, Britz, Dominik, Mücklich, Frank
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.10.2020; Springer Nature B.V
• Subjects: Bainite; Characterization and Evaluation of Materials; Chemistry and Materials Science; Histograms; Image processing; Image segmentation; Materials Science; Metallic Materials; Nanotechnology; Parameters; Structural Materials; Surfaces and Interfaces; Task complexity; Technical Article; Thin Films; Local orientation and direction analysis; Bainite; Segmentation; Microstructure; Steel; Region growing
• ISSN: 2192-9262; 2192-9270
• DOI: 10.1007/s13632-020-00676-9

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 so-called 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.