知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

44 records (took 0.023 seconds)

    Model and ensemble compression for metric learning
    1.
    发明授权
    Model and ensemble compression for metric learning 有权

    公开(公告)号：US11281993B2

    公开(公告)日：2022-03-22

    申请号：US15832671

    申请日：2017-12-05

    Applicant: Apple Inc.

    Inventor： Joshua M. Susskind ,  Feng Tang ,  Chen Huang ,  Shih-Yu Sun ,  Walter A. Talbot

    IPC: G06F3/0488 ,  G06N20/00 ,  G06F3/04883 ,  G06N5/02 ,  G06F3/04817

    Abstract: Systems and processes for metric learning distillation are disclosed herein. In accordance with one example, a method includes, at an electronic device, at an electronic device having one or more processors and memory, receiving a first plurality of vectors from a first model, receiving a second plurality of vectors from a second model, determining a first plurality of vector distances based on the first plurality of vectors, generating a first matrix based on the first plurality of vector distances, determining a second plurality of vector distances based on the second plurality of vectors, generating a second matrix based on the second plurality of vector distances, comparing the first matrix with the second matrix, and adjusting the second model based on the comparison of the first matrix and the second matrix.

    Network performance by including attributes
    2.
    发明授权
    Network performance by including attributes 有权

    公开(公告)号：US10915734B2

    公开(公告)日：2021-02-09

    申请号：US16277544

    申请日：2019-02-15

    Applicant: Apple Inc.

    Inventor： Atulit Kumar ,  Joerg A. Liebelt ,  Onur C. Hamsici ,  Feng Tang

    IPC: G06K9/00 ,  G06N3/04

    Abstract: An image captured using a camera on a device (e.g., a mobile device) may be operated on by one or more processes to determine properties of a user's face in the image. A first process may determine one or more first properties of the user's face in the image. A second process operating downstream from the first process may determine at least one second property of the user's face in the image. The second process may use at least one of the first properties from the first process to determine the second property.

    Robust face detection
    3.
    发明授权
    Robust face detection 有权

    公开(公告)号：US10769414B2

    公开(公告)日：2020-09-08

    申请号：US16119842

    申请日：2018-08-31

    Applicant: Apple Inc.

    Inventor： Atulit Kumar ,  Thorsten Gernoth ,  Feng Tang

    IPC: G06K9/00 ,  G06T7/73

    Abstract: A neural network may implement a face detection process on a mobile device or computer system. An image captured using a camera on the device may be processed using the face detection process. The face detection process may provide a bounding box for the face detected in the image. The face detected in the image may have any orientation. The face detected in the image may include either a whole face of the user or only a partial face of the user. The face detection process may provide face detection that is substantially invariant to exposure in the captured image. The face may also be detected over a wide range of distances between the camera and the face of the user.

    ROBUST FACE DETECTION
    4.
    发明申请
    ROBUST FACE DETECTION 审中-公开

    公开(公告)号：US20190370529A1

    公开(公告)日：2019-12-05

    申请号：US16119842

    申请日：2018-08-31

    Applicant: Apple Inc.

    Inventor： Atulit Kumar ,  Thorsten Gernoth ,  Feng Tang

    IPC: G06K9/00 ,  G06T7/73

    Abstract: A neural network may implement a face detection process on a mobile device or computer system. An image captured using a camera on the device may be processed using the face detection process. The face detection process may provide a bounding box for the face detected in the image. The face detected in the image may have any orientation. The face detected in the image may include either a whole face of the user or only a partial face of the user. The face detection process may provide face detection that is substantially invariant to exposure in the captured image. The face may also be detected over a wide range of distances between the camera and the face of the user.

    PROCESS FOR UPDATING TEMPLATES USED IN FACIAL RECOGNITION
    5.
    发明申请
    PROCESS FOR UPDATING TEMPLATES USED IN FACIAL RECOGNITION 审中-公开

    公开(公告)号：US20190042866A1

    公开(公告)日：2019-02-07

    申请号：US15881261

    申请日：2018-01-26

    Applicant: Apple Inc.

    Inventor： Eslam A. Mostafa ,  Haitao Guo ,  Feng Tang

    IPC: G06K9/00 ,  G06K9/20 ,  G06F21/32

    Abstract: Templates used for a facial recognition process for authentication of a user to use a device may be updated by the device as features of the user change over time. Features of the user may gradually change over time due to changes such as facial hair changes, haircuts, gaining/losing weight, and/or aging. Updating the templates used for the facial recognition process may allow the user to continue being authenticated as features of the user change without the need for additional enrollments of the user.

    MODEL AND ENSEMBLE COMPRESSION FOR METRIC LEARNING
    6.
    发明申请
    MODEL AND ENSEMBLE COMPRESSION FOR METRIC LEARNING 审中-公开

    公开(公告)号：US20180157992A1

    公开(公告)日：2018-06-07

    申请号：US15832671

    申请日：2017-12-05

    Applicant: Apple Inc.

    Inventor： Joshua M. Susskind ,  Feng Tang ,  Chen Huang ,  Shih-Yu Sun ,  Walter A. Talbot

    IPC: G06N99/00 ,  G06N5/02

    CPC classification number: G06N20/00 ,  G06F3/04817 ,  G06F3/04883 ,  G06N5/02

    Abstract: Systems and processes for metric learning distillation are disclosed herein. In accordance with one example, a method includes, at an electronic device, at an electronic device having one or more processors and memory, receiving a first plurality of vectors from a first model, receiving a second plurality of vectors from a second model, determining a first plurality of vector distances based on the first plurality of vectors, generating a first matrix based on the first plurality of vector distances, determining a second plurality of vector distances based on the second plurality of vectors, generating a second matrix based on the second plurality of vector distances, comparing the first matrix with the second matrix, and adjusting the second model based on the comparison of the first matrix and the second matrix.

    Detection of identity changes during facial recognition enrollment process
    9.
    发明授权
    Detection of identity changes during facial recognition enrollment process 有权

    公开(公告)号：US10769415B1

    公开(公告)日：2020-09-08

    申请号：US16119798

    申请日：2018-08-31

    Applicant: Apple Inc.

    Inventor： Eslam A. Mostafa ,  Hao Tang ,  Feng Tang

    IPC: G06K9/00 ,  H04N5/225 ,  G06K9/62 ,  G06T7/521

    Abstract: A device with a camera may utilize an enrollment process to capture images of an authorized user to enroll the user for a facial recognition authorization process. The enrollment process may include one or more processes that identify if an identity of the authorized user (e.g., the subject of the enrollment process) has switched during the enrollment process. The processes may include detection and verification of the switch in identities by comparing features of subjects in images as the images are captured during the enrollment process. If the identity of the subject is determined to be switched from the authorized user during the enrollment process, the enrollment process may be restarted. Additionally, clustering of feature vectors from the enrollment images may be used to remove outlying feature vectors that may be generated from one or more images of a subject other than the authorized user.

    PERIOCULAR FACIAL RECOGNITION SWITCHING
    10.
    发明申请
    PERIOCULAR FACIAL RECOGNITION SWITCHING 审中-公开

    公开(公告)号：US20200082157A1

    公开(公告)日：2020-03-12

    申请号：US16277282

    申请日：2019-02-15

    Applicant: Apple Inc.

    Inventor： Joshua M. Susskind ,  Walter A. Talbott ,  Shih-Yu Sun ,  Feng Tang

    IPC: G06K9/00 ,  G06K9/32

    Abstract: A facial recognition authentication process operating on a device may capture an image of a user using a camera on the device. The facial recognition authentication process may include operating a full face facial recognition authentication process on the captured image or operating a partial face facial recognition authentication process on the captured image. The process may determine which process to operate (either full face or partial face) based on an assessment of an amount of occlusion in the captured image. The partial face facial recognition authentication process may be operated when there is at least some occlusion of selected features (e.g., nose and/or mouth) on the user's face in the captured image.

Patent Agency Ranking