Machine-readable food packaging film

    公开(公告)号:US10074046B2

    公开(公告)日:2018-09-11

    申请号:US15460518

    申请日:2017-03-16

    CPC classification number: G06K19/06037 G06K7/1095

    Abstract: In one embodiment, a sidewalk-facing display window of a retail store is treated to scatter (or absorb) a portion of incident light, in a narrow wavelength spectral band. A machine-readable pattern, which encodes an identifier, is projected onto the treated window from outside the store. The reflection (absorption) of that projected pattern, within the narrow spectral band, escapes notice of shoppers on the sidewalk. Yet if a shopper captures imagery of a product displayed on the other side of the display window, using a mobile device camera, the pattern is captured with the imagery, and can be analyzed to decode the identifier. The mobile device can use this decoded identifier to access online information about the displayed product, for presentation to the shopper on the mobile device display. The technology is particularly suited for wearable computing devices, and more generally enables glass windows to subliminally convey digital information to image sensors conveyed by passing shoppers. A great variety of other features and arrangements are also detailed.

    Context-related arrangements
    85.
    发明授权

    公开(公告)号:US09883396B2

    公开(公告)日:2018-01-30

    申请号:US15273375

    申请日:2016-09-22

    Abstract: In one arrangement, a first device presents a display that is based on context data, derived from one or more of its sensors. This display is imaged by a camera in a second device. The second device uses context data from its own sensors to assess the information in the captured imagery, and makes a determination about the first device. In another arrangement, social network friend requests are automatically issued, or accepted, based on contextual similarity. In yet another arrangement, delivery of a message is triggered by a contextual circumstance other than (or in addition to) location. In still another arrangement, two or more devices automatically establish an ad hoc network (e.g., Bluetooth pairing) based on contextual parallels. In still another arrangement, historical context information is archived and used in transactions with other devices, e.g., in challenge-response authentication. A great number of other features and arrangements—many involving head-mounted displays—are also detailed.

    LEARNING SYSTEMS AND METHODS
    88.
    发明申请

    公开(公告)号:US20170243317A1

    公开(公告)日:2017-08-24

    申请号:US15446811

    申请日:2017-03-01

    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