Computer Vision and Machine Learning Techniques for Optical Micrograph Defect Classification Using a Novel Gray Thresholding Technique

Machine learning is explored to assess optical micrographs for defects and in identifying machine settings of laser-based powder bed fusion additively manufactured (AM) steel. Two algorithms are explored for defect analysis: Naïve Bayes and random forest. Additionally, a novel technique for discriminating density analysis of optical micrographs of highly dense builds is developed. These tools aim to fill gaps in both rapid qualification of AM components and allow for faster, more accurate parameter sweeps for development of optimal printing parameters for new materials. The Naïve Bayes algorithm outperforms the random forest algorithm in this study because it allows for less rigidly linear classification subsets. The novel gray thresholding routine is compared to all available automatic thresholding methods available in freeware ImageJ and is shown to discriminate between high density optical micrographs ( ≥ ≥ 99.5% dense) better in nearly all cases. Additionally, it solves the problem of how small variations in threshold levels outside of the optimal level result in significantly different reported density measurements by generating the optimal threshold for every micrograph.