Non-destructive automatic die-level defect detection of counterfeit microelectronics using machine vision

The goal of this paper is to automate the process of IC counterfeit detection using Non-destructive Imaging Techniques. The defects targeted in this study are the most prevalent die-level defects with possible multi-dimensional features, making their non-destructive detection challenging. Non-destructive X-ray microtomography is a powerful tool to obtain 3D internal information on microelectronics but usually results in large datasets and a stack of more than a thousand 2D images requiring a subject matter expert to investigate them individually for potential defects. Such detection method is time-consuming, costly and subjective being largely dependent on the level of expertise, experience and diligence. Our method addresses those challenges by incorporating machine vision instead of human input for detection.