Abstract: It is tried and tested that optical and electronic microscopy images of steel material specimen could be categorized into phases on preset ferrite/pearlite, spheroidized, ferrite, pearlite, and martensite type microstructures with image processing and statistical analysis which include the machine learning techniques. Though several popular classifiers were get the reasonable class-labelling accuracy, the random forest was virtually the best choice in terms of overall performance and usability. The present categorizing classifier could assist in choosing the appropriate pattern recognition method from our library for various steel microstructures, which we have recently reported. That is, the combination of the categorizing and pattern recognizing methods provides a total solution for automatic classification of a wide range of steel microstructures. In this work we present an innovative approach for metallurgical sample identification and error calculation based on imaging classification with classic machine learning algorithms.
Keywords: Metallography, Machine Learning, Microscopy, Metallurgy
| DOI: 10.17148/IJARCCE.2019.81118