公开(公告)号：US20190287230A1

公开(公告)日：2019-09-19

申请号：US16106341

申请日：2018-08-21

Applicant: KLA-TENCOR CORPORATION

Inventor： Shaoyu Lu ,  Li He ,  Sankar Venkataraman

IPC: G06T7/00

Abstract: 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.

公开(公告)号：US10789703B2

公开(公告)日：2020-09-29

申请号：US16106341

申请日：2018-08-21

Applicant: KLA-TENCOR CORPORATION

Inventor： Shaoyu Lu ,  Li He ,  Sankar Venkataraman

IPC: G06T7/00 ,  G06N3/04

Abstract: 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.

公开(公告)号：US10074167B2

公开(公告)日：2018-09-11

申请号：US15355509

申请日：2016-11-18

Applicant: KLA-Tencor Corporation

Inventor： Saibal Banerjee ,  Ashok Kulkarni ,  Shaoyu Lu

IPC: G06T7/00

CPC classification number: G06T7/0004 ,  G06T7/001 ,  G06T7/337 ,  G06T2207/10061 ,  G06T2207/30148

Abstract: 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.

公开(公告)号：US20170161888A1

公开(公告)日：2017-06-08

申请号：US15355509

申请日：2016-11-18

Applicant: KLA-Tencor Corporation

Inventor： Saibal Banerjee ,  Ashok Kulkarni ,  Shaoyu Lu

IPC: G06T7/00

CPC classification number: G06T7/0004 ,  G06T7/001 ,  G06T7/337 ,  G06T2207/10061 ,  G06T2207/30148

Abstract: 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.