利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

91 条记录 (耗时 0.034 秒)

    LIVENESS DETECTION
    54.
    发明公开
    LIVENESS DETECTION 审中-公开

    公开(公告)号：US20230343070A1

    公开(公告)日：2023-10-26

    申请号：US18333357

    申请日：2023-06-12

    申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

    发明人： Wenhan Luo ,  Yaodong Wang ,  Wei Liu

    IPC分类号： G06V10/764 ,  G06V40/16 ,  G06V10/82 ,  G06V20/52 ,  G06V40/18 ,  G06V40/40

    CPC分类号： G06V10/764 ,  G06V40/168 ,  G06V40/172 ,  G06V10/82 ,  G06V20/52 ,  G06V40/165 ,  G06V40/193 ,  G06V40/40

    摘要： An access system, including a reception device, a recognition server, and an access control device. The reception device acquires a plurality of images of an access object. The recognition server includes a liveness detection apparatus determines corresponding eigenvectors according to the plurality of images of the access object, captures an action behavior of the access object according to a relative change between the determined eigenvectors, and determines the access object as a live body in response to capturing the action behavior of the access object. The recognition server performs identity recognition on the access object when the access object is the live body so that the access control device configures an access permission for the access object that completes the identity recognition successfully, and the access object controls, according to the configured access permission, an access barrier of a specified work region to perform a release action.

    Image fusion method, model training method, and related apparatuses
    56.
    发明授权
    Image fusion method, model training method, and related apparatuses 有权

    公开(公告)号：US11776097B2

    公开(公告)日：2023-10-03

    申请号：US17336561

    申请日：2021-06-02

    申请人： Tencent Technology (Shenzhen) Company Limited

    发明人： Haozhi Huang ,  Senzhe Xu ,  Shimin Hu ,  Wei Liu

    IPC分类号： G06T5/50 ,  G06N3/04 ,  G06N3/08

    CPC分类号： G06T5/50 ,  G06N3/04 ,  G06N3/08 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221

    摘要： Methods, devices, and storage medium for fusing at least one image are disclosed. The method includes obtaining a first to-be-fused image and a second to-be-fused image, the first to-be-fused image comprising first regions, and the second to-be-fused image comprising second regions; obtaining a first feature set according to the first to-be-fused image and obtaining a second feature set according to the second to-be-fused image; performing first fusion processing on the first to-be-fused image and the second to-be-fused image by using a shape fusion network model to obtain a third to-be-fused image, the third to-be-fused image comprising at least one first encoding feature and at least one second encoding feature; and performing second fusion processing on the third to-be-fused image and the first to-be-fused image by using a condition fusion network model to obtain a target fused image. Model training methods, apparatus, and storage medium are also disclosed.

    Neural network model training method and device, and time-lapse photography video generating method and device
    58.
    发明授权
    Neural network model training method and device, and time-lapse photography video generating method and device 有权

    公开(公告)号：US11429817B2

    公开(公告)日：2022-08-30

    申请号：US16892587

    申请日：2020-06-04

    申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

    发明人： Wenhan Luo ,  Lin Ma ,  Wei Liu

    IPC分类号： G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06V20/40 ,  G06T15/20

    摘要： The present disclosure describes methods, devices, and storage medium for generating a time-lapse photography video with a neural network model. The method includes obtaining a training sample. The training sample includes a training video and an image set. The method includes obtaining through training according to the training sample, a neural network model to satisfy a training ending condition, the neural network model comprising a basic network and an optimization network, by using the image set as an input to the basic network, the basic network being a first generative adversarial network for performing content modeling, generating a basic time-lapse photography video as an output of the basic network, using the basic time-lapse photography video as an input to the optimization network, the optimization network being a second generative adversarial network for performing motion state modeling, and generating an optimized time-lapse photography video as an output of the optimization network.

    Face image generation method and apparatus, device, and storage medium
    59.
    发明授权
    Face image generation method and apparatus, device, and storage medium 有权

    公开(公告)号：US11380050B2

    公开(公告)日：2022-07-05

    申请号：US17235456

    申请日：2021-04-20

    申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

    发明人： Xue Fei Zhe ,  Yonggen Ling ,  Lin Chao Bao ,  Yi Bing Song ,  Wei Liu

    IPC分类号： G06T17/00 ,  G06T7/70 ,  G06K9/62 ,  G06N3/02 ,  G06V40/16

    摘要： A face image generation method includes: determining, according to a first face image, a three dimensional morphable model (3DMM) corresponding to the first face image as a first model; determining, according to a reference element, a 3DMM corresponding to the reference element as a second model, the reference element representing a posture and/or an expression of a target face image; determining, according to the first model and the second model, an initial optical flow map corresponding to the first face image, and deforming the first face image according to the initial optical flow map to obtain an initial deformation map; obtaining, through a convolutional neural network, an optical flow increment map and a visibility probability map that correspond to the first face image; and generating the target face image according to the first face image, the initial optical flow map, the optical flow increment map, and the visibility probability map.