Invention Grant
- Patent Title: Data augmentation for convolutional neural network-based defect inspection
-
Application No.: US15720272Application Date: 2017-09-29
-
Publication No.: US10402688B2Publication Date: 2019-09-03
- Inventor: Bjorn Brauer , Vijay Ramachandran , Richard Wallingford , Scott Allen Young
- Applicant: KLA-Tencor Corporation
- Applicant Address: US CA Milpitas
- Assignee: KLA-Tencor Corporation
- Current Assignee: KLA-Tencor Corporation
- Current Assignee Address: US CA Milpitas
- Agency: Hodgson Russ LLP
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06K9/62 ; G06T7/00 ; G06N3/04 ; G06N3/08

Abstract:
Systems and methods for providing an augmented input data to a convolutional neural network (CNN) are disclosed. Wafer images are received at a processor. The wafer image is divided into a plurality of references images each associated with a die in the wafer image. Test images are received. A plurality of difference images are created by differences the test images with the reference images. The reference images and difference images are assembled into the augmented input data for the CNN and provided to the CNN.
Public/Granted literature
- US20180157933A1 Data Augmentation for Convolutional Neural Network-Based Defect Inspection Public/Granted day:2018-06-07
Information query