知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.013 seconds)

    DETECTION OF PHYSICAL TAMPERING ON DOCUMENTS
    2.
    发明公开
    DETECTION OF PHYSICAL TAMPERING ON DOCUMENTS 审中-公开

    公开(公告)号：US20230419715A1

    公开(公告)日：2023-12-28

    申请号：US17850602

    申请日：2022-06-27

    Applicant: PAYPAL, INC.

    Inventor： Jiazheng Zhang ,  Yuzhen Zhuo ,  Jiyi Zhang

    IPC: G06V30/418 ,  G06V30/413 ,  G06V30/42

    CPC classification number: G06V30/418 ,  G06V30/413 ,  G06V30/42

    Abstract: Methods and systems are presented for detecting physical tampering on a document based on analyzing an image of the document. When the image of the document is obtained, multiple contours are identified in the image based on pixel characteristics of the image. Dimension attributes of the contours are determined. Contours that are determined to correspond to borders or texts of the documents based on the dimension attributes are eliminated. A second text detection process based on a polygon method is performed on at least one remaining contour to determine whether the at least one remaining contour links multiple text elements together. The document is determined to have been physically manipulated when at least on contour remains in the image.

    IMAGE FORGERY DETECTION VIA HEADPOSE ESTIMATION
    3.
    发明申请
    IMAGE FORGERY DETECTION VIA HEADPOSE ESTIMATION 有权

    公开(公告)号：US20220318597A1

    公开(公告)日：2022-10-06

    申请号：US17236085

    申请日：2021-04-21

    Applicant: PayPal, Inc.

    Inventor： Xiaodong Yu ,  Jiazheng Zhang ,  Jiyi Zhang ,  Quan Jin Ferdinand Tang ,  Shanshan Peng ,  Yuzhen Zhuo ,  Hong Qian ,  Runmin Wen

    IPC: G06N3/04 ,  G06N3/08 ,  G06T7/70 ,  G06T7/11

    Abstract: Systems and/or techniques for facilitating image forgery detection via headpose estimation are provided. In various embodiments, a system can receive a document from a client device. In various cases, the system can identify, by executing a first trained machine learning model, an object that is depicted in the document. In various instances, the system can determine, by executing a second trained machine learning model, a pose of the object. In various aspects, the system can determine, by executing a third trained machine learning model, whether the document is authentic or forged based on the pose of the object. In various embodiments, the system can, in response to determining that the document is forged, transmit an unsuccessful validation message to the client device.

    CONTENT EXTRACTION BASED ON HOP DISTANCE WITHIN A GRAPH MODEL
    6.
    发明公开
    CONTENT EXTRACTION BASED ON HOP DISTANCE WITHIN A GRAPH MODEL 审中-公开

    公开(公告)号：US20240153296A1

    公开(公告)日：2024-05-09

    申请号：US17983908

    申请日：2022-11-09

    Applicant: Paypal, Inc.

    Inventor： Yanfei Dong ,  Yuan Deng ,  Jiazheng Zhang ,  Francesco Gelli ,  Ting Lin ,  Yuzhen Zhuo ,  Hewen Wang ,  Soujanya Poria

    IPC: G06V30/19 ,  G06V10/74 ,  G06V30/18 ,  G06V30/414

    CPC classification number: G06V30/1916 ,  G06V10/761 ,  G06V30/18181 ,  G06V30/414

    Abstract: A method of categorizing text entries on a document can include determining, for each of a plurality of text bounding boxes in the document, respective text, respective coordinates, and respective input embeddings. The method may further include defining a graph of the plurality of bounding boxes, the graph comprising a plurality of connections among the plurality of bounding boxes, each connection comprising a first and second bounding box and zero or more respective intermediate bounding boxes. The method may further include determining a respective attention value for each connection according to a quantity of intermediate bounding boxes in the connection and, based on a the respective attention values and a transformer-based machine learning model applied to the respective input embeddings and respective coordinates, determining output embeddings for each bounding box and, based on the respective output embeddings, generating a bounding box label for each bounding box.

    MACHINE LEARNING MODEL FOR IMAGE FORGERY DETECTION
    7.
    发明公开
    MACHINE LEARNING MODEL FOR IMAGE FORGERY DETECTION 审中-公开

    公开(公告)号：US20240320471A1

    公开(公告)日：2024-09-26

    申请号：US18189044

    申请日：2023-03-23

    Applicant: PayPal, Inc.

    Inventor： Zhe Chen ,  Panpan Qi ,  Jiazheng Zhang ,  Jiyi Zhang ,  Quan Jin Ferdinand Tang

    IPC: G06N3/045 ,  G06F21/31 ,  G06N3/0895

    CPC classification number: G06N3/045 ,  G06F21/31 ,  G06N3/0895

    Abstract: Techniques for predicting whether a submission includes a forged image. A computer system receives a submission from a user that includes an image and image metadata, such as an identifier for the user and a User-Agent string value. An image pixel embedding is generated from the image, and a profile embedding is generated from the image metadata. The image embedding is indicative of whether the image is similar to known image forgeries. The profile embedding is generated from a user activity embedding indicative of User-Agent values associated with the user identifier. The profile embedding is generated using a machine learning model that uses stored parameters to associate user activity, device information, and forgery groups. The profile embedding thus indicates whether the user is associated with known image forgeries. The image pixel embedding and profile embedding are then used by a neural network to output a forgery prediction.

    FRAUD DETECTION FOR SIGNED DOCUMENTS
    8.
    发明公开
    FRAUD DETECTION FOR SIGNED DOCUMENTS 审中-公开

    公开(公告)号：US20240144728A1

    公开(公告)日：2024-05-02

    申请号：US18051580

    申请日：2022-11-01

    Applicant: PAYPAL, INC.

    Inventor： Quan Jin Ferdinand Tang ,  Jiyi Zhang ,  Jiazheng Zhang ,  Shanshan Peng ,  Jia Wen Lee

    IPC: G06V40/30 ,  G06Q50/26 ,  G06V10/70 ,  G06V30/18 ,  G06V30/19 ,  G06V30/416

    CPC classification number: G06V40/33 ,  G06Q50/265 ,  G06V10/70 ,  G06V30/18 ,  G06V30/19093 ,  G06V30/416

    Abstract: Methods and systems are presented for signed document image analysis and fraud detection. An image of a document may be received from a user's device. A first layer of a machine learning engine is used to identify a signature and a name of the user within different areas of the received image. A second layer of the machine learning engine is used to extract a plurality of features from the different areas of the image. The plurality of features includes at least one visual feature representing the signature and at least one textual feature representing the name. A combined feature representation of the signature and the name is generated based on the plurality of features extracted from the image. A third layer of the machine learning engine is used to determine whether the signature of the user has been digitally altered, based on the combined feature representation.

Patent Agency Ranking