Combining unsupervised and supervised learning in microscopy enables defect analysis of a full 4H-SiC wafer
This work addresses the challenge of handling large-scale microscopy data for semiconductor defect analysis, which is incremental as it integrates existing techniques into a pipeline.
The researchers tackled the problem of automating defect detection in semiconductor microscopy by combining unsupervised and supervised learning to create an image analysis pipeline, enabling the extraction of defect types and positions from a full wafer stitched from about 40,000 images.
Detecting and analyzing various defect types in semiconductor materials is an important prerequisite for understanding the underlying mechanisms as well as tailoring the production processes. Analysis of microscopy images that reveal defects typically requires image analysis tasks such as segmentation and object detection. With the permanently increasing amount of data that is produced by experiments, handling these tasks manually becomes more and more impossible. In this work, we combine various image analysis and data mining techniques for creating a robust and accurate, automated image analysis pipeline. This allows for extracting the type and position of all defects in a microscopy image of a KOH-etched 4H-SiC wafer that was stitched together from approximately 40,000 individual images.