Enhancing Quantification of Inclusions in PoDFA Micrographs Through Integration of Deterministic and Deep Learning Image Analysis Algorithms

The assessmentAssessment of aluminumAluminum melt cleanlinessCleanliness has traditionally relied on labor-intensive and subjective manual processes. The present study builds upon prior digital image analysis to quantify inclusionsInclusions in micrographs of PoDFAPoDFA samples. Through the integration of deterministic methodsMethod, unsupervised Machine LearningMachine Learning (ML) (ML), and neural networksNeural networks, cleanlinessCleanliness data comparable to PoDFAPoDFA grid assessmentsAssessment has been achieved. Overcoming the challenge of generating sufficient and accurate training data for neural networksNeural networks, the suggested approach has been refined. Enhanced isolation strategies for target classes have resulted in higher-quality training data, elevating the prediction accuracy of the neural networkNeural networks. Post-processingProcessing of neural networkNeural networks predictions has also been improved. The integrated approach presented here demonstrates more reliable cleanlinessCleanliness data than previous implementations. Offering a promising alternative to manual PoDFAPoDFA assessmentsAssessment, this integrated approach improves efficiency and reduces human biases.