Digimarc Corporation

Other

Intel Corporation

Digimarc Coporation

Ravi K Sharma

Tony F Rodriguez

Geoffrey B Rhoads

Alastair M Reed

John Douglas Lord

Brett Alan Bradley

Hugh L Brunk

John F Stach

Shankar Thagadur Shivappa

Vojtech Holub

Osama M Alattar

Tomas Filler

Robert G Lyons

Ajith Mulki Kamath

Aparna R Gurijala

Adnan M Alattar

William Y Conwell

Brett T Hannigan

Yang Bai

Jacob L Boles

Brian T MacIntosh

Ammon E Gustafson

Scott M Long

Matthew M Weaver

Kenneth Lee Levy

Donald Haaga

Trent J Brundage

Vahid Sedighianaraki

David A Cushman

Farid Ahmed

Tyler J McKinley

Eric D Evans

Marc D Miller

Rajeeb Hazra

Joel R Meyer

Eliot Rogers

Kurt M Eaton

Utkarsh Deshmukh

Lance Lixin Shen

Bruce L Davis

Andrew Evan Klonsky

Phillip Andrew Seder

Stephen K Decker

Arlene K Kasai

Emma C Sinclair

Christopher A Ambiel

Clay Davidson

Jeffery B Schulte

Jeffrey B Schulte

Rajan Samtani

Sierra K Modro

Richard F Gibson

Adnam M Alattar

Adnan V Alattar

Aparna Gurijala

John A Scriven

Tomas Denemark

Hugh L Brunk Brunk

Two stages of a convolutional neural network are linked by an interconnect that effects a spatial transposition of array data. The spatial transposition can include rotation, scaling, or translation (e.g., in x- or y-directions). A parameter characterizing the transposition (e.g., a parameter identifying rotation angle) can be learned by the same training process that is also used to learn other network parameters, such as layer coefficients. Additionally, or alternatively, data input to a neural network comprises—for each pixel in a patch of imagery—plural data that each indicates a relationship between the value of the pixel, and the value of a neighboring pixel. Some such neural networks can be trained to indicate the presence of a digital watermark signal in the patch of imagery—or a parameter characterizing such a digital watermark signal. Other features and arrangements are also detailed.

Enhanced neural network systems and methods

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.

Image processing arrangements

A steganographic digital watermark signal is decoded from host imagery without requiring a domain transformation for signal synchronization, thereby speeding and simplifying the decoding operation. In time-limited applications, such as in supermarket point-of-sale scanners that attempt watermark decode operations on dozens of video frames every second, the speed improvement allows a greater percentage of each image frame to be analyzed for watermark data. In battery-powered mobile devices, avoidance of repeated domain transformations extends battery life. A great variety of other features and arrangements, including machine learning aspects, are also detailed.

Image-based pose determination

A plastic item, such as a beverage bottle, conveys 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 conveys 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 lacks the 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. A great number of other features and arrangements are also detailed.

Recycling methods and systems, and related plastic containers

A thermoplastic resin, such as PET, is molded to define a 2D code signal, such as a digital watermark pattern. The mold can comprise an array of hole or spike features, some of which are directly vented to atmospheric pressure. A network of channels can link the other features to the directly-vented features, so all features are vented. A mold comprising spike features can form a digital watermark pattern on an item such that the watermark payload is decodable both from the side of the item that contacted the mold, and also from the opposite, non-contact side of the item. To aid entry of viscous thermoplastic among the very fine elemental features of a mold representing a watermark signal pattern, the features can be overlapped, forming a connected binary mark having larger features. A variety of other improvements and arrangements are also detailed.

Signaling arrangements employing molded thermoplastics

Signal processing devices and methods estimate a geometric transform of an image. One method measures correlation between a transformed reference signal component and an image, updates, based on the measured correlation that is below a threshold, coordinates of the reference signal component to a location within a neighborhood around the coordinates of the transformed reference signal component; determines a new geometric transform that transforms the reference signal components to updated coordinates; and applies the new geometric transform to extract encoded digital data from the image.

Signal processors and methods for estimating geometric transformations of images for digital data extraction

Audio signal processing enhances audio watermark embedding and detecting processes. Audio signal processes include audio classification and adapting watermark embedding and detecting based on classification. Advances in audio watermark design include adaptive watermark signal structure data protocols, perceptual models, and insertion methods. Perceptual and robustness evaluation is integrated into audio watermark embedding to optimize audio quality relative the original signal, and to optimize robustness or data capacity. These methods are applied to audio segments in audio embedder and detector configurations to support real time operation. Feature extraction and matching are also used to adapt audio watermark embedding and detecting.

Multi-mode audio recognition and auxiliary data encoding and decoding

Watermarking media content, in combination with blockchain and distributed storage networks, prevents the proliferation of Deepfake content. Digital watermarks are embedded in the audio and video tracks of video clips of trusted content producers at the time the videos are captured or before they are distributed. The watermarks are detected at the social media network's portals, nodes, and back ends. The embedded watermark imparts a unique identifier to the video, that links it to a blockchain. The watermarks also allow video source tracking, integrity verification, and alteration localization. The watermark detectors can be standalone software applications, or they can be integrated with other applications. They are used to perform three main tasks: (1) they alert the Internet user when he watches an inauthentic news video, so that he may discard it, (2) they prevent a Deepfake content from propagating through the network (3) they perform forensic analysis to help track and remove Deepfake content postings.

System for mitigating the problem of deepfake media content using watermarking

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.

Methods and arrangements for sorting items, useful in recycling

Images depicting items in a waste flow on a conveyor belt are provided to two analysis systems. The first system processes images to decode digital watermark payload data found on certain of the items (e.g., plastic containers). This payload data is used to look up corresponding attribute metadata for the items in a database, such as the type of plastic in each item, and whether the item was used as a food container or not. The second analysis system can be a spectroscopy system that determines the type of plastic in each item by its absorption characteristics. When the two systems conflict in identifying the plastic type, a sorting logic processor applies a rule set to arbitrate the conflict and determine which plastic type is most likely. The item is then sorted into one of several different bins depending on a combination of the final plastic identification, and whether the item was used as a food container or not. A variety of other features and arrangements are also detailed.

Arrangements for digital marking and reading of items, useful in recycling

Artwork carrying machine readable data is generated by editing artwork according to a data signal or transforming the data signal into artwork. The machine-readable data signal is generated from a digital payload and converted into an image tile. Artwork is edited according to the image tile by moving graphic elements, adapting intersections of lines, or altering line density, among other techniques. Artwork is generated from the data signal by skeletonizing it and applying morphological operators to a skeletal representation, such as a medial axis transform. Artistic effects are introduced by filtering the data signal with directional blurring or shape filters.

Generating artistic designs encoded with robust, machine-readable data

Mobile device positioning employs various forms of audio signal structures and detection methodologies. In one method, detection of an audio signal from a first source enables construction of a signal to facilitate detection of an audio signal from another source. Signals detected from these sources enable positioning of the mobile device receiving those signals. Another method forms audio signals transmitted from audio sources so that they have parts that add constructively and parts that differentiate the sources to enable positioning. Another audio signal based positioning method adaptively switches among positioning methods so that positioning remains operative as a mobile device moves toward and away from the sources. Another method tracks positioning history, evaluates it for errors and performs error mitigation to improve accuracy. Various other positioning technologies are detailed as well.

Mobile device indoor navigation

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&#x2014;some employing recognition technologies in addition to neural networks. A great number of other features and arrangements are also detailed.

Growing community of inventors

Portland, OR, United States of America

Ravi K Sharma