Machine learning (ML)-assisted approaches are becoming essential for reliable failure analysis in microelectronic components, particularly through advanced digital image analysis techniques. As microelectronic components continue to shrink in size and increase in complexity, ensuring their reliability becomes a critical challenge. Failures often originate from material-level defects, making accurate detection and analysis essential for both manufacturing and operational reliability. This research integrates computational tools with materials science to enhance microscopic characterization, focusing on defect detection and structural analysis of material interfaces.

In this work, we developed defect and phase detection models using advanced machine learning and computer vision approaches that are more reliable, with detection accuracy close to or sometimes better than manual or existing approaches. The work includes different use-cases such as void, phases, anomalies and chipping detection, have an accuracy ranging from 86 % to 94 % and has advantage of being time-efficient by a factor of 20x to 30x for different tasks. Each use-case microscopy image data from different sources such as optical light microscopy, scanning electron microscopy, infra-red microscopy and X-ray.