Digimarc Corporation

Joel R Meyer

Geoffrey B Rhoads

Tony F Rodriguez

Kenneth Lee Levy

William Y Conwell

Ravi K Sharma

Hugh L Brunk

Osama M Alattar

Brett Alan Bradley

Tomas Filler

Ajith Mulki Kamath

Burt W Perry

John F Stach

Vojtech Holub

Adnan M Alattar

Sean Calhoon

Hoyet Harrison Andrews, Iii

Emma C Sinclair

Tomas Denemark

Rajan Samtani

Hugh L Brunk Brunk

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

Imagery captured by an autonomous robot is analyzed to discern digital watermark patterns. In some embodiments, identical but geometrically-inconsistent digital watermark patterns are discerned in an image frame, to aid in distinguishing multiple depicted instances of a particular item. In other embodiments, actions of the robot are controlled or altered in accordance with image processing performed by the robot on a digital watermark pattern. The technology is particularly described in the context of retail stores in which the watermark patterns are encoded, e.g., on product packaging, shelving, and shelf labels. A great variety of other features and arrangements are also detailed.

Image processing methods and arrangements useful in automated store shelf inspections

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&#x2014;some involving designing classifiers so as to combat classifier copying&#x2014;are also detailed.

The parameters of an optical code are optimized to achieve improved signal robustness, reliability, capacity and/or visual quality. An optimization program can determine spatial density, dot distance, dot size and signal component priority to optimize robustness. An optical code generator employs these parameters to produce an optical code at the desired spatial density and robustness. The optical code is merged into a host image, such as imagery, text and graphics of a package or label, or it may be printed by itself, e.g., on an otherwise blank label or carton. A great number of other features and arrangements are also detailed.

Generating and reading optical codes with variable density to adapt for visual quality and reliability

This disclosure describes novel methods for generating unique copies of content. One method combines the functions of the master copy and unique copy watermarks. In particular, the method generates a unique copy by varying the manner in which the master copy watermark is embedded in unique copies of a content item. In one embodiment, the master copy watermark is repeated within the content item and its location is varied in a unique pattern that comprises the unique copy watermark. The unique copy is generated by producing a copy in which master copy watermarks are embedded in a unique pattern. For instance in one embodiment, the locations of the master copy watermarks in the content item are represented as a vector of delta values in which each delta value corresponds to the distance between a corresponding instance of the master copy watermark, and a neighboring instance of the master copy watermark. This vector is stored in a transaction record in association with transaction information, such as information identifying the master copy and information associated with the unique copy. Other ways of representing the unique pattern of attributes of the master copy watermark are also possible. In other embodiments, properties of the master copy watermark other than its location are varied through the content. The unique copy watermark is conveyed in the vector of deltas in these properties of the master copy watermark. Some examples of these properties of the master copy watermark signal include phase characteristics (e.g., the phase shift of a watermark carrier signal), frequency magnitude characteristics, etc. These properties are varied in a manner that does not alter the information carried in the master copy watermark. However, it does provide a variation that creates a unique copy, and the unique copy watermark is conveyed in this variation. The variation in location of the instances of the master copy watermark can be in different domains, such as a spatial domain, a time domain, a time-space domain, a transform domain (including frequency transform domains), a compressed domain, etc.

Content serialization by varying content properties, including varying master copy watermark properties

Methods and apparatuses are provided for determining a first fingerprint of audio or video data. The first fingerprint is stored in a database or record including information pertaining to a first user or first account. The audio or video content is altered to yield a different version of the audio or video content, and a second fingerprint is determined from the different version of the audio or video content. The second fingerprint is stored in a database or recording including information pertaining to a second user or second account.

Deriving multiple fingerprints from audio or video content

The present disclosure relates to processing media content (e.g., video or audio signals). One claim recites a method including: receiving first content comprising a video portion or an audio portion, the first content being received over a network from a user; utilizing a multi-purpose electronic processor programmed as a content identifier module, deriving identifying data from data representing picture portions of the video portion or from data representing audible portions of the audio portion of the first content; with reference to a computerized database or computerized repository, determining a first promotional opportunity associated with the identifying data, in which the first proportional opportunity comprises an opportunity to purchase second content, the second content being related to&#x2014;but different than&#x2014;the first content, and determining a second, different promotional opportunity associated with the identifying data if another instance of the identifying data is thereafter received; and providing information regarding the first promotional opportunity or the second, different promotional opportunity. Of course, other claims and combinations are provided too.

Systems and methods using digital watermarking and identifier extraction to provide promotional opportunities

The presently claimed invention relates to audio and video processing. One claim recites a method including: obtaining streaming audio or video on a handheld wireless device, the handheld wireless device comprising: i) a programmed electronic processor, and ii) memory; using the programmed electronic processor, analyzing data representing the audio or video to extract identifying information there from; obtaining a device identifier or user identifier from the memory; communicating the identifying information and the device identifier or user identifier to a database as part of a request to add a title corresponding to the streaming audio or video to a media collection associated with the device identifier or user identifier, and in which the title is associated with the identifying information. Of course, other claims and combinations are provided too.

Systems and methods of managing audio and other media

A method for operating an electronic gaming system captures an image of a gaming object, extracts identifying information from the image of the gaming object, and uses the extracted identifying information to reference a database to determine a behavior associated with the identifying information. The method returns data to the gaming system to execute or control the behavior of the gaming system in response to the gaming object. Various system configurations for this method as well as unique applications of it are also disclosed.

Interactive gaming objects

The present invention relates generally to fingerprinting (e.g., deriving identifying data from audio or other media content). One claim recites a method including: obtaining identifying data derived with fingerprinting from data representing audio elements of an audio signal or derived with fingerprinting from data representing video picture elements of a video signal, the audio signal or video signal corresponding to a media signal captured by a wireless handheld device; determining a media title that corresponds to the identifying data; determining usage rights associated with at least one of the media title or a user of the wireless handheld device; identifying the user of the wireless handheld device or a library of the media titles that is associated with the user of the wireless handheld device; and adding the media title to the library of media titles that is associated with the user if so permitted by the usage rights. Of course, other claims and combinations are provided as well.

Embedded data in gaming objects is used to authenticate the gaming object and to enhance the gaming experience in gambling venues The gaming object is authenticated automatically using information about the venue encoded in the gaming objects. The behavior of electronic gambling game systems is enhanced by extracting covert data from gaming objects and using the extracted data to control behavior of the gambling game.

Embedded data in gaming objects for authentication and association of behavior information

A digital watermark detection method uses a matched filtering technique on a log polar re-mapping of a watermarked signal to detect peaks associated with a repetitive structure of a watermark.

Computing distortion of media signals using embedded data with repetitive structure and log-polar mapping

Computing distortion of media signals embedded data with repetitive structure and log-polar mapping

Media objects are transformed into active, connected objects via identifiers embedded into them or their containers. In the context of a user's playback experience, a decoding process extracts the identifier from a media object and possibly additional context information and forwards it to a server. The server, in turn, maps the identifier to an action, such as returning metadata, re-directing the request to one or more other servers, requesting information from another server to identify the media object, etc. The linking process applies to broadcast objects as well as objects transmitted over networks in streaming and compressed file formats.

Growing community of inventors

Lake Oswego, OR, United States of America

Joel R Meyer