公开(公告)号：US20220388213A1

公开(公告)日：2022-12-08

申请号：US17835775

申请日：2022-06-08

Applicant: Digimarc Corporation

Inventor： Tomas Filler ,  Vojtech Holub ,  Nicholas Anderson

IPC: B29C45/37 ,  B23K26/362 ,  B65D1/02

Abstract: 2D code patterns, such as digital watermark patterns, are formed on plastic objects by injection molding. In some implementations, a marked cell of the code pattern is not formed by a single mark on the mold surface, but by multiple discrete marks. Such marks can be exceedingly small (e.g., 50 microns or less—smaller than the width of a human hair), yet the resulting code pattern on the molded object is still readable from a distance. The small scale of the marks assures that the code pattern does not detract from object aesthetics, while also speeding the mold-marking process. Style transfer networks are employed in some implementations. The detailed technologies facilitate digital marking and identification of a great number of consumer plastic objects, thereby aiding recovery of such objects for recycling. Many other features and arrangements are also detailed.

公开(公告)号：US20240412188A1

公开(公告)日：2024-12-12

申请号：US18639588

申请日：2024-04-18

Applicant: Digimarc Corporation

Inventor： Vojtech Holub ,  Tomas Filler ,  Eric D. Evans ,  Alexander Hull ,  Ethan Lyons ,  Daniel J. Stotts ,  Christopher M. Haverkate ,  Nicholas Anderson ,  Dimitris Chachlakis

IPC: G06Q20/20 ,  G06K7/14 ,  G06V10/25 ,  G06V10/26

Abstract: A retail checkout system decodes machine-readable indicia from a composite image frame produced from a sequence of captured image frames. Different regions in the composite image are derived from different ones of the image frames in the captured sequence. Another embodiment generates a composite image frame from image frames captured with different camera focus settings. Still other embodiments concern neural networks, including their training to segment different items presented on a retail checkout surface. Other neural network embodiments discern on which of two items a machine readable indicia appears, when the visual context is ambiguous. A variety of other features and arrangements are also detailed.