利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

90 条记录 (耗时 0.019 秒)

    SYSTEM FOR PRESERVING IMAGE AND ACOUSTIC SENSITIVITY USING REINFORCEMENT LEARNING
    23.
    发明申请
    SYSTEM FOR PRESERVING IMAGE AND ACOUSTIC SENSITIVITY USING REINFORCEMENT LEARNING 有权

    公开(公告)号：US20230048759A1

    公开(公告)日：2023-02-16

    申请号：US17975903

    申请日：2022-10-28

    申请人： BANK OF AMERICA CORPORATION

    发明人： Madhusudhanan Krishnamoorthy

    IPC分类号： G06V20/40 ,  G06N3/08 ,  G06K9/62 ,  G06F16/45 ,  G06F16/435 ,  G06V10/88 ,  G06V10/75

    摘要： Systems, computer program products, and methods are described herein for preserving image and acoustic sensitivity using reinforcement learning. The present invention is configured to initiate a file editing engine on the audiovisual file to separate the audiovisual file into a video component and an audio component; initiate a convolutional neural network (CNN) algorithm on the video component to identify one or more sensitive portions in the one or more image frames; initiate an audio word2vec algorithm on the audio component to identify one or more sensitive portions in the audio component; initiate a masking algorithm on the one or more image frames and the audio component; generate a masked video component and a masked audio component based on at least implementing the masking action policy; and bind, using the file editing engine, the masked video component and the masked audio component to generate a masked audiovisual file.

    Devices and methods to convert conventional imagers into lock-in cameras
    25.
    发明授权
    Devices and methods to convert conventional imagers into lock-in cameras 有权

    公开(公告)号：US11291370B2

    公开(公告)日：2022-04-05

    申请号：US16422906

    申请日：2019-05-24

    申请人： HI LLC

    发明人： Jamu Alford ,  Adam Marblestone

    IPC分类号： A61B5/00 ,  G06T11/00 ,  G16H30/40 ,  A61B5/145 ,  G06V10/12 ,  G06V10/88 ,  G06V10/24

    摘要： Disclosed herein are devices and methods for modifying a conventional imager to have functional features similar to that of a lock-in camera. Optical mask devices are configured to be coupled to conventional imager sensors and the configuration of the mask devices can be adjusted to acquire image data in rapid succession. One variation of an optical mask device comprises a substrate comprising a pattern of light-blocking and light-transmitting regions and an attachment structure for coupling the optical mask device to the imager. The substrate is configured to adjust the position of the light-blocking regions and light-transmitting regions relative to the light-sensing region of the imager based on a set of one or more predetermined substrate configurations. In some variations, the mask device and/or the imager sensor may be mechanically moved relative to each other based on the set of one or more predetermined substrate configurations.

    FILTER LEARNING DEVICE, FILTER LEARNING METHOD, AND NON-TRANSITORY COMPUTER-READABLE MEDIUM
    26.
    发明申请
    FILTER LEARNING DEVICE, FILTER LEARNING METHOD, AND NON-TRANSITORY COMPUTER-READABLE MEDIUM 有权

    公开(公告)号：US20220092871A1

    公开(公告)日：2022-03-24

    申请号：US17428168

    申请日：2019-02-06

    申请人： NEC Corporation

    发明人： Takahiro TOIZUMI ,  Masato TSUKADA

    IPC分类号： G06V10/88 ,  G06V10/44 ,  G06V10/70

    摘要： An object is to provide a filter learning device capable of optimizing recognition processing using features obtained from the characteristics of light. The filter learning device (10) according to the present disclosure includes an optical filter unit (11) for extracting a filter image from an image for learning by using a filter condition determined according to a filter parameter, a parameter updating unit (12) for updating the filter parameter with a result obtained by executing image analysis processing on the filter image, and a sensing unit (13) for sensing an input image by using a physical optical filter that satisfies a filter condition determined according to the updated filter parameter.