中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

106 records (took 0.023 seconds)

    Methods for identifying audio or video content
    81.
    发明授权
    Methods for identifying audio or video content 有权
    用于识别音频或视频内容的方法

    公开(公告)号：US08688999B2

    公开(公告)日：2014-04-01

    申请号：US13937995

    申请日：2013-07-09

    Applicant: Digimarc Corporation

    Inventor： William Y. Conwell

    IPC: G06F17/30 ,  G06K9/62 ,  H04L29/06 ,  G06Q50/00

    CPC classification number: G06F17/30743 ,  G06F17/30017 ,  G06F17/30023 ,  G06F17/30265 ,  G06F17/30784 ,  G06K9/62 ,  G06N5/048 ,  G06Q10/00 ,  G06Q50/01 ,  G06Q50/18 ,  G06Q50/265 ,  H04L9/3247 ,  H04L63/08

    Abstract: Methods and systems for identifying audio and video entertainment content are provided. Certain shortcomings of fingerprint-based content identification can be redressed through use of human-reviewers in a first party's social networking site environment. Access to a copy of a possible fingerprint-based match of user uploaded content is provided to a second party via a queue of an online interface provided by the first party. In response to providing access to the copy of the user uploaded content, manual human assessment data is obtained from the second party through the online interface. The manual human assessment data indicating a result of a comparison of the copy of the user uploaded content and data associated with reference content by one or more human reviewer(s). The manual human assessment data is used in concluding that the reference content corresponds with the user uploaded content.

    Abstract translation: 提供用于识别音频和视频娱乐内容的方法和系统。 基于指纹的内容识别的某些缺点可以通过在第一方社交网站环境中使用人类审阅者进行纠正。 经由第一方提供的在线界面的队列，向第二方提供对用户上载内容的可能的基于指纹的匹配的副本的访问。 响应于提供对用户上传内容的副本的访问，通过在线界面从第二方获得手动人为评估数据。 指示由一个或多个人类审阅者比较用户上载内容的副本和与参考内容相关联的数据的结果的手动人类评估数据。 使用手动人力评估数据来确定参考内容对应于用户上传的内容。

    Methods and arrangements for sorting items, useful in recycling
    85.
    发明授权
    Methods and arrangements for sorting items, useful in recycling 有权

    公开(公告)号：US11878327B2

    公开(公告)日：2024-01-23

    申请号：US17470674

    申请日：2021-09-09

    Applicant: Digimarc Corporation

    Inventor： Ravi K Sharma ,  Tomas Filler ,  Vojtech Holub ,  Osama M. Alattar ,  Hugh L. Brunk ,  John D. Lord ,  Geoffrey B. Rhoads ,  William Y. Conwell ,  Ajith M. Kamath

    IPC: B07C5/34 ,  B07C5/342

    CPC classification number: B07C5/3412 ,  B07C5/3422 ,  B07C2501/0045

    Abstract: A plastic item, such as a beverage bottle, can convey two distinct digital watermarks, encoded using two distinct signaling protocols. A first, printed label watermark conveys a retailing payload, including a Global Trade Item Number (GTIN) used by a point-of-sale scanner in a retail store to identify and price the item when presented for checkout. A second, plastic texture watermark may convey a recycling payload, including data identifying the composition of the plastic. The use of two different signaling protocols assures that a point-of-sale scanner will not spend its limited time and computational resources working to decode the recycling watermark, which may lack data needed for retail checkout. In some embodiments, a recycling apparatus makes advantageous use of both types of watermarks to identify the plastic composition of the item (e.g., relating GTIN to plastic type using an associated database), thereby increasing the fraction of items that are correctly identified for sorting and recycling. In other embodiments the plastic item (or a label thereon) bears only a single watermark. A great number of other features and arrangements are also detailed.

    LASER MARKING OF MACHINE-READABLE CODES
    88.
    发明公开
    LASER MARKING OF MACHINE-READABLE CODES 审中-公开

    公开(公告)号：US20230177297A1

    公开(公告)日：2023-06-08

    申请号：US18077914

    申请日：2022-12-08

    Applicant: Digimarc Corporation

    Inventor： Tomas Filler ,  Vojtech Holub ,  Hugh L. Brunk ,  Adnan M. Alattar ,  William Y. Conwell

    IPC: G06K19/06

    CPC classification number: G06K19/06037

    Abstract: A surface is laser-etched to convey a 2D machine-readable code pattern. Various strategies are detailed to minimize the etching time. Some strategies include modifying the code pattern to reduce a path length traveled by the laser. Some strategies include modifying the code pattern to make it sub-optimal, i.e., making the code pattern a less-faithful approximation of an ideal code pattern. In some embodiments the etched surface is the surface of a plastic container, and the code pattern conveys information indicating the type of plastic of which the container is manufactured. A variety of other features and arrangements are also detailed.

    LEARNING SYSTEMS AND METHODS
    89.
    发明申请
    LEARNING SYSTEMS AND METHODS 有权

    公开(公告)号：US20220270199A1

    公开(公告)日：2022-08-25

    申请号：US17694396

    申请日：2022-03-14

    Applicant: Digimarc Corporation

    Inventor： Tony F. Rodriguez ,  Osama M. Alattar ,  Hugh L. Brunk ,  Joel R. Meyer ,  William Y. Conwell ,  Ajith M. Kamath

    IPC: G06T1/00 ,  G06F21/16 ,  G06K9/62 ,  G06V10/24 ,  G06V20/20

    Abstract: A sequence of images depicting an object is captured, e.g., by a camera at a point-of-sale terminal in a retail store. The object is identified, such as by a barcode or watermark that is detected from one or more of the images. Once the object's identity is known, such information is used in training a classifier (e.g., a machine learning system) to recognize the object from others of the captured images, including images that may be degraded by blur, inferior lighting, etc. In another arrangement, such degraded images are processed to identify feature points useful in fingerprint-based identification of the object. Feature points extracted from such degraded imagery aid in fingerprint-based recognition of objects under real life circumstances, as contrasted with feature points extracted from pristine imagery (e.g., digital files containing label artwork for such objects). A great variety of other features and arrangements—some involving designing classifiers so as to combat classifier copying—are also detailed.

    Learning systems and methods
    90.
    发明授权
    Learning systems and methods 有权

    公开(公告)号：US10902539B2

    公开(公告)日：2021-01-26

    申请号：US15446811

    申请日：2017-03-01

    Applicant: Digimarc Corporation

    Inventor： Tony F. Rodriguez ,  Osama M. Alattar ,  Hugh L. Brunk ,  Joel R. Meyer ,  William Y. Conwell ,  Ajith Mulki Kamath

    IPC: G06K9/62 ,  G06T1/00 ,  G06K9/00 ,  G06F21/16 ,  G06K9/32

    Abstract: A sequence of images depicting an object is captured, e.g., by a camera at a point-of-sale terminal in a retail store. The object is identified, such as by a barcode or watermark that is detected from one or more of the images. Once the object's identity is known, such information is used in training a classifier (e.g., a machine learning system) to recognize the object from others of the captured images, including images that may be degraded by blur, inferior lighting, etc. In another arrangement, such degraded images are processed to identify feature points useful in fingerprint-based identification of the object. Feature points extracted from such degraded imagery aid in fingerprint-based recognition of objects under real life circumstances, as contrasted with feature points extracted from pristine imagery (e.g., digital files containing label artwork for such objects). A great variety of other features and arrangements—some involving designing classifiers so as to combat classifier copying—are also detailed.

Patent Agency Ranking