Deep learning in metallography: adapting a grain size determination model to develop the new comparison charts for ISO 643

Abstract The determination of average grain size is an important component in the microstructural characterization of metallic materials. The grain size is usually determined using the intercept and comparison methods, but there are problems with the relatively time-consuming intercept method and the low accuracy of the comparison method. In this paper, a new model is proposed to realize the task of automatic grain size grading using a combination of traditional image processing and deep learning. Deep learning semantic segmentation and image classification are used to achieve the grading of different quality images. The model is capable of extracting and complementing grain boundaries and calculating the pixel area of the grains. The accuracy of the model was tested on metallographic phases of pure iron and austenitic stainless steel. Using this model, grain size comparison charts were produced for ISO 643 based on real metallographic photographs.