利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

7 条记录 (耗时 0.033 秒)

    Method and apparatus for authentication of a 3D structure
    2.
    发明授权
    Method and apparatus for authentication of a 3D structure 有权

    公开(公告)号：US10789463B2

    公开(公告)日：2020-09-29

    申请号：US15985091

    申请日：2018-05-21

    申请人： ALPVISION S.A.

    发明人： Martin Kutter ,  Fred Jordan

    IPC分类号： G06K9/00 ,  G07D7/00 ,  G07D7/2033 ,  G07D7/202 ,  G06K7/14 ,  G06T7/00

    摘要： New authentication features are proposed that are visible, can be authenticated with a mobile equipment and yet are challenging to counterfeit. In a possible embodiment, the surface of the authentication feature may have three-dimensional characteristics, which can be recognized by a handheld camera, such as a smartphone camera, while it cannot be easily reproduced by a simple scan and print procedure. In a further possible embodiment, at least two different viewpoints of the authentication feature may be acquired using a smartphone camera and the resulting images may be analyzed using the smartphone processor to identify the three-dimensional characteristics of the authentication feature. The manufacturing of the feature may be performed at a low cost by embossing the three dimensional structure on a surface. The authentication feature may be carried by a self-adhesive label or directly embedded on the product packaging.

    Authentication machine learning from multiple digital presentations
    5.
    发明授权
    Authentication machine learning from multiple digital presentations 有权

    公开(公告)号：US11461582B2

    公开(公告)日：2022-10-04

    申请号：US16956028

    申请日：2018-12-20

    申请人： ALPVISION S.A.

    发明人： Frederic Jordan ,  Nicolas Rudaz ,  Yves Delacretaz ,  Martin Kutter

    IPC分类号： G06K9/62 ,  G06T7/70

    摘要： A machine learning system may automatically produce classifier algorithms and configuration parameters by selecting them into a set of predetermined unitary algorithms and associated parametrization values. Multiple digital representations of input object items may be produced by varying the position and orientation of the object to be classified and/or of the sensor to capture a digital representation of the object, and/or by varying a physical environment parameter which changes the digital representation capture of the object by the sensor. A robot arm or a conveyor may vary the object and/or the sensor positions and orientations. The machine learning system may employ generic programming to facilitate the production of classifiers suitable for the classification of multiple digital representations of input object items. The machine learning system may automatically generate reference template signals as configuration parameters for the unitary algorithms to facilitate the production of classifiers suitable for the classification of multiple digital representations of input object items.