Machine Learning for Microstructure Quantification of Different Material Classes

Abstract

Abstract Material characterization is one of the major challenges faced in the field of materials research. The general approach is the assessment of quantitative properties, which are dependent on the utilization of destructive/non-destructive techniques. Conventional methods require the user to manually assess the obtained micrographs to identify the microstructural patterns followed by physical tests to quantify properties and characterization. A recent development in this area is the use of the concept of machine learning (ML) in image segmentation and analysis. Over the years, research in this area has resulted in the development of stable, robust and reliable systems, which yield consistently good results. This paper is aimed at introducing the use of one such machine learning approach based on Artificial Neural Networks (ANN) for image segmentation and quantification of material properties and discussion of some use cases. The results of the ML based method are compared with the results obtained from the traditional threshold based segmentation method.