公开(公告)号：US20200320660A1

公开(公告)日：2020-10-08

申请号：US16853327

申请日：2020-04-20

Applicant: Digimarc Corporation

Inventor： Ajith M. Kamath ,  Christopher A. Ambiel ,  Utkarsh Deshmukh ,  Andi R. Castle ,  Christopher M. Haverkate

IPC: G06T1/00 ,  G06K19/06 ,  G06T11/20 ,  G06N3/08

Abstract: Features from a style image are adapted to express a machine-readable code. For example, grains of rice depicted in a style image may be positioned to create a pattern mimicking that of a machine-readable code. The resulting output image can then be used as a graphical component in product packaging (e.g., as a background, border, or pattern fill), while also serving to convey a product identifier to a compliant reader device (e.g., a retail point-of-sale terminal). In some embodiments, a neural network is trained to apply a particular style image to machine readable codes. A great variety of other features and arrangements are also detailed.

公开(公告)号：US20250028919A1

公开(公告)日：2025-01-23

申请号：US18675848

申请日：2024-05-28

Applicant: Digimarc Corporation

Inventor： Vojtech Holub ,  Utkarsh Deshmukh ,  Tomas Filler

IPC: G06K7/14 ,  G06K19/06 ,  G06T1/00 ,  G06T3/40 ,  G06T7/73 ,  G06V10/20 ,  G06V10/30 ,  G06V10/32 ,  H04N23/56

Abstract: The present technology relates to image signal processing. One aspect of the present technology involves analyzing reference imagery gathered by a camera system to determine which parts of an image frame offer high probabilities of—relative to other image parts—containing decodable signal data. Another aspect of the present technology whittles-down such determined image frame parts based on detected content (e.g., a cereal box) vs expected background within such determined image frame parts.

公开(公告)号：US20240104682A1

公开(公告)日：2024-03-28

申请号：US18223352

申请日：2023-07-18

Applicant: Digimarc Corporation

Inventor： Ajith M. Kamath ,  Christopher A. Ambiel ,  Utkarsh Deshmukh ,  Andi R. Castle ,  Christopher M. Haverkate

IPC: G06T1/00 ,  G06F16/18 ,  G06K19/06 ,  G06N3/08 ,  G06T11/20

CPC classification number: G06T1/0092 ,  G06F16/1858 ,  G06K19/06103 ,  G06N3/08 ,  G06T11/20

Abstract: Features from a style image are adapted to express a machine-readable code. For example, grains of rice depicted in a style image may be positioned to create a pattern mimicking that of a machine-readable code. The resulting output image can then be used as a graphical component in product packaging (e.g., as a background, border, or pattern fill), while also serving to convey a product identifier to a compliant reader device (e.g., a retail point-of-sale terminal). In some embodiments, a neural network is trained to apply a particular style image to machine readable codes. A great variety of other features and arrangements are also detailed.

公开(公告)号：US20230316386A1

公开(公告)日：2023-10-05

申请号：US18176700

申请日：2023-03-01

Applicant: Digimarc Corporation

Inventor： Ravi K. Sharma ,  Tomas Filler ,  Utkarsh Deshmukh ,  Vahid Sedighianaraki ,  William Y. Conwell

IPC: G06Q30/0601 ,  G06V10/82 ,  G06F18/214 ,  G06F18/22 ,  G06F18/2431 ,  G06V10/10 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06V10/46 ,  G06V20/00

CPC classification number: G06Q30/0641 ,  G06V10/82 ,  G06F18/214 ,  G06F18/22 ,  G06F18/2431 ,  G06V10/17 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06V10/462 ,  G06V20/00 ,  G06N3/04

Abstract: Aspects of the detailed technologies concern training and use of neural networks for fine-grained classification of large numbers of items, e.g., as may be encountered in a supermarket. Mitigating false positive errors is an exemplary area of emphasis. Novel network topologies are also detailed—some employing recognition technologies in addition to neural networks. A great number of other features and arrangements are also detailed.

公开(公告)号：US11704765B2

公开(公告)日：2023-07-18

申请号：US16853327

申请日：2020-04-20

Applicant: Digimarc Corporation

Inventor： Ajith M. Kamath ,  Christopher A. Ambiel ,  Utkarsh Deshmukh

IPC: G06T1/00 ,  G06K19/06 ,  G06T11/20 ,  G06N3/08 ,  G06F16/18

CPC classification number: G06T1/0092 ,  G06F16/1858 ,  G06K19/06103 ,  G06N3/08 ,  G06T11/20

Abstract: Features from a style image are adapted to express a machine-readable code. For example, grains of rice depicted in a style image may be positioned to create a pattern mimicking that of a machine-readable code. The resulting output image can then be used as a graphical component in product packaging (e.g., as a background, border, or pattern fill), while also serving to convey a product identifier to a compliant reader device (e.g., a retail point-of-sale terminal). In some embodiments, a neural network is trained to apply a particular style image to machine readable codes. A great variety of other features and arrangements are also detailed.

公开(公告)号：US10664722B1

公开(公告)日：2020-05-26

申请号：US15726290

申请日：2017-10-05

Applicant: Digimarc Corporation

Inventor： Ravi K. Sharma ,  Tomas Filler ,  Utkarsh Deshmukh ,  Vahid Sedighianaraki

IPC: G06K9/62 ,  G06Q30/06 ,  G06N3/04 ,  G06N3/08

Abstract: Aspects of the detailed technologies concern training and use of neural networks for fine-grained classification of large numbers of items, e.g., as may be encountered in a supermarket. Mitigating false positive errors is an exemplary area of emphasis. Novel network topologies are also detailed—some employing recognition technologies in addition to neural networks. A great number of other features and arrangements are also detailed.

公开(公告)号：US20190266749A1

公开(公告)日：2019-08-29

申请号：US16141587

申请日：2018-09-25

Applicant: Digimarc Corporation

Inventor： Geoffrey B. Rhoads ,  Utkarsh Deshmukh ,  John D. Lord

IPC: G06T7/73 ,  G06T1/00 ,  G06T5/00 ,  G06T7/00

Abstract: The geometric pose of a patch of watermark data is estimated based on the position of a similar, but non-identical, patch of information within a data structure. The information in the data structure corresponds to a tiled array of calibration patterns that is sampled along at least three non-parallel paths. In a particular embodiment, the calibration patterns are sampled so that edges are globally-curved, yet locally-flat. Use of such information in the data structure enables enhanced pose estimation, e.g., speeding up operation, enabling pose estimation from smaller patches of watermark signals, and/or enabling pose estimation from weaker watermark signals. A great variety of other features and arrangements are also detailed.