Kla Tencor Corporation

Shaoyu Lu

Ashok V Kulkarni

Saibal Banerjee

Sankar Venkataraman

Li He

Autoencoder-based, semi-supervised approaches are used for anomaly detection. Defects on semiconductor wafers can be discovered using these approaches. The model can include a variational autoencoder, such as a one that includes ladder networks. Defect-free or clean images can be used to train the model that is later used to discover defects or other anomalies.

Semi-supervised anomaly detection in scanning electron microscope images

Noise induced by pattern-of-interest (POI) image registration and POI vicinity design patterns in intra-die inspection is reduced. POI are grouped into alignment groups by co-occurrence of proximate registration targets. The alignment groups are registered using the co-occurrence of proximate registration targets. Registration by voting is performed, which can measure a degree that each of the patterns-of-interest is an outlier. POI are grouped into at least one vicinity group with same vicinity design effects.

Growing community of inventors

Fremont, CA, United States of America

Shaoyu Lu