Knowledge Integration in Steel Microstructure Analysis Using Unsupervised Image Segmentation and Supervised Machine Learning Techniques

This study presents a methodology for analyzing bainitic microstructures in steel using image segmentation techniques and machine learning methods. Images of steel microstructures were processed using a superpixel segmentation algorithm, which generated image segments based on grayscale intensity. The histograms of values in grayscale of those segments served as input for classification models such as decision trees, random forests, and the KNN algorithm. Experimental results demonstrated that this method enables effective microstructure classification, including the identification of segments containing bainite. A comparison of algorithms revealed the superiority of random forests in terms of stability and accuracy. Results also show that small segments provide better final results. The obtained results indicate the potential for further development of this method using more advanced neural networks for automated steel microstructure analysis.