中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5 records (took 0.015 seconds)

    Reconstructor and contrastor for anomaly detection
    1.
    发明授权
    Reconstructor and contrastor for anomaly detection 有权

    公开(公告)号：US10733722B2

    公开(公告)日：2020-08-04

    申请号：US15983342

    申请日：2018-05-18

    Applicant: NEC Laboratories America, Inc.

    Inventor： Alexandru Niculescu-Mizil ,  Eric Cosatto ,  Felix Wu

    IPC: G06T7/00 ,  H04N19/132 ,  H04N19/17 ,  G16H50/70 ,  G16H50/20 ,  G06T11/20 ,  G16H20/30 ,  G16H30/40 ,  G06T11/00

    Abstract: Systems and methods for detecting and correcting defective products include capturing at least one image of a product with at least one image sensor to generate an original image of the product. An encoder encodes portions of an image extracted from the original image to generate feature space vectors. A decoder decodes the feature space vectors to reconstruct the portions of the image into reconstructed portions by predicting defect-free structural features in each of the portions according to hidden layers trained to predict defect-free products. Each of the reconstructed portions are merged into a reconstructed image of a defect-free representation of the product. The reconstructed image is communicated to a contrastor to detect anomalies indicating defects in the product.

    RECONSTRUCTOR AND CONTRASTOR FOR ANOMALY DETECTION
    3.
    发明申请
    RECONSTRUCTOR AND CONTRASTOR FOR ANOMALY DETECTION 审中-公开

    公开(公告)号：US20180374207A1

    公开(公告)日：2018-12-27

    申请号：US15983342

    申请日：2018-05-18

    Applicant: NEC Laboratories America, Inc.

    Inventor： Alexandru Niculescu-Mizil ,  Eric Cosatto ,  Felix Wu

    IPC: G06T7/00 ,  H04N19/17 ,  H04N19/132

    Abstract: Systems and methods for detecting and correcting defective products include capturing at least one image of a product with at least one image sensor to generate an original image of the product. An encoder encodes portions of an image extracted from the original image to generate feature space vectors. A decoder decodes the feature space vectors to reconstruct the portions of the image into reconstructed portions by predicting defect-free structural features in each of the portions according to hidden layers trained to predict defect-free products. Each of the reconstructed portions are merged into a reconstructed image of a defect-free representation of the product. The reconstructed image is communicated to a contrastor to detect anomalies indicating defects in the product.

    Anomaly detection with predictive normalization
    4.
    发明授权
    Anomaly detection with predictive normalization 有权

    公开(公告)号：US10964011B2

    公开(公告)日：2021-03-30

    申请号：US16703349

    申请日：2019-12-04

    Applicant: NEC Laboratories America, Inc.

    Inventor： Eric Cosatto ,  Felix Wu ,  Alexandru Niculescu-Mizil

    IPC: G06T7/00 ,  G06K9/62 ,  G06N3/08 ,  G06N3/04

    Abstract: A method is provided for model training to detect defective products. The method includes sampling training images of a product to (i) extract image portions therefrom made of a center patch and its context and (ii) black-out the center patch. The method further includes performing unsupervised back-propagation training of a Contextual Auto-Encoder (CAE) model using (i) the image portions with the blacked-out center patch as an input and, (ii) the center patch as a target output and, (iii) an image-based loss function, to obtain a trained CAE model. The method also includes sampling positive and negative center-patch-sized portions from the training images. The method additionally includes normalizing, using the trained CAE model, the positive and negative center-patch-sized portions. The method further includes performing supervised training of a classifier model using the normalized positive and negative center-patch-sized portions to obtain a trained supervised classifier model for detecting the defective products.

Patent Agency Ranking