Abstract: The presently claimed invention relates to deriving or extracting information from audio, images and video. One claim recites a method of operating a network filter. The network includes a plurality of network nodes, the network filter is for filtering video or audio. The method includes: monitoring video or audio traffic to a particular network node; identifying a first video or audio at the particular network node through deriving identifying data from data representing the first video or audio, the deriving utilizes at least one programmed multi-purpose computer processor; determining additional information associated with the first video or audio based at least in part on the identifying information; and notifying the network node of the presence of the additional information.

Abstract: Imagery, video, maps or signs are embedded with plural-bit data in the form of digital watermarking. In one embodiment, a method includes obtaining a media signal representing an image or video; introducing digital watermarking into the media signal, the digital watermarking slightly altering samples of the media signal; and the digital watermarking changing across the media signal so as to convey first information related to at least a first area depicted in the image or within data representing a first portion of the video in the media signal and second, different information related to at least a second area depicted in the image or within data representing a second portion of the video in the media signal. Other embodiments are provided as well.

Abstract: The presently claimed invention relates generally to steganographic encoding. One claim recites a method including: obtaining data representing a first graphic; utilizing a multi-purpose computer processor configured for steganographically data hiding to hide a signal in the data representing the first graphic; obtaining a copy of the first graphic including a steganographically hidden signal therein; storing the copy of the first graphic in electronic memory or integrated circuitry. A steganographically hidden signal in the data representing the first graphic and the steganographically hidden signal in the copy of the first graphic are related. Of course, other combinations are provided as well.

Abstract: This invention deals with recommendation systems. The first embodiment is an off-the-shelf recommendation system is described, where it is easy to integrate with the website database and uses a web service for recommendations, as well as easy to integrate with email. The system receives client ID, item ID and user ID, and returns recommended item IDs. The recommendations include similar items, related items, related users, items likely to be acted upon by a given user (labeled likely items), and users likely to act upon an item (labeled likely users). The recommendations include categorical training, where recommended items are based upon similar categories, where the category types include as product type and brand. The recommendations include similar-to-related training, where similar items are used to find related items. These two intelligent methods work for items with no, few or numerous actions.

Abstract: The ability to remove a watermark from encoded content (e.g., an image) opens the possibility of various novel applications. Several such applications are detailed. One employs a reversible watermark in conjunction with a second (robust) watermark. In this arrangement, the payload of the reversible watermark conveys information about the robust watermark (e.g., encoding parameters, or an error signal), permitting removal of the robust watermark from an uncorrupted encoded image. By such arrangements, the encoded image can be fully restored to its pristine, unencoded state even if several different watermarks have been applied.

Abstract: The presently claimed invention relates to deriving or extracting information from audio, images and video. One claim recites a method of operating a network filter. The network includes a plurality of network nodes, the network filter is for filtering video or audio. The method includes: monitoring video or audio traffic to a particular network node; identifying a first video or audio at the particular network node through deriving identifying data from data representing the first video or audio, the deriving utilizes at least one programmed multi-purpose computer processor; determining additional information associated with the first video or audio based at least in part on the identifying information; and notifying the network node of the presence of the additional information.

Abstract: The presently claimed invention relates generally to steganographic encoding. One claim recites a method including: obtaining data representing a first graphic; utilizing a multi-purpose computer processor configured for steganographically data hiding to hide a signal in the data representing the first graphic; obtaining a copy of the first graphic including a steganographically hidden signal therein; storing the copy of the first graphic in electronic memory or integrated circuitry. A steganographically hidden signal in the data representing the first graphic and the steganographically hidden signal in the copy of the first graphic are related. Of course, other combinations are provided as well.

Abstract: The ability to remove a watermark from an encoded image opens the possibility of various novel applications. Several such applications are detailed. One employs a reversible watermark in conjunction with a second (robust) watermark. In this arrangement, the payload of the reversible watermark conveys information about the robust watermark (e.g., encoding parameters, or an error signal), permitting removal of the robust watermark from an uncorrupted encoded image. By such arrangements, the encoded image can be fully restored to its pristine, unencoded state even if several different watermarks have been applied.

Abstract: Steganographic methods for encoding auxiliary data into a host signal are used to authenticate physical and electronic objects. One claim recites an object comprising: a first graphic provided on an object surface, and a storage device carried by the object. The storage device includes a second graphic stored therein. The first and second graphics are related graphics, and the second graphic includes first steganographic encoding including a plural-bit payload. Of course, other combinations are provided as well.

Abstract: Maps and/or signs are embedded with plural-bit data in the form of digital watermarks. In one implementation, an apparatus is provided to read two or more digital watermarks embedded within a map. Each of the two or more digital watermarks includes location information for a respective map location. The two or more digital watermarks are embedded through alterations to data representing the map; the alterations are generally imperceptible to a human observer of the map. The apparatus includes: a global positioning system receiver to determine a physical location of said apparatus; an input to receive data corresponding to at least a portion of the respective map area; a processor or electronic processing circuitry to extract the location information from the input data and to correlate the physical location with the extracted location information; and an output to output an indication of a relative correlation between the physical location and watermark location information.

Abstract: The present invention relates to systems and methods for managing images or video and related information. In one embodiment, geographic information system (GIS) layer information is registered or aligned to an image or video using digital watermark information embedded within the image or video. Other embodiments are provided as well.

Abstract: A variety of systems and embodiments are disclosed. One embodiment provides a method including: maintaining a database including a plurality of records stored therein; obtaining first information derived from image or video data, the first information being derived remotely relative to performance of said method, the first information comprising a reduced-bit representation of the image or video data itself; determining whether the first information has been previously received with reference to at least the plurality of records stored in the database; and disregarding a request or action associated with the first information if the first information has been previously received. Of course, other combinations are provided and claimed as well.

Abstract: Steganographic methods for encoding auxiliary data into a host signal are used to authenticate physical and electronic objects. One claim recites an object comprising: a first graphic provided on an object surface, and a storage device carried by the object. The storage device includes a second graphic stored therein. The first and second graphics are related graphics, and the second graphic includes first steganographic encoding including a plural-bit payload. Of course, other combinations are provided as well.

Abstract: The present invention relates generally to digital watermarking and steganography. In one embodiment, a method is provided including: obtaining a plurality of imagery, each item of the plurality of imagery including steganographic encoding, the steganographic encoding including multi-bit data; detecting the multi-bit data from the plurality of imagery, wherein the multi-bit data is associated with geolocation metadata; and providing a geographic path associated with the plurality of imagery based at least in part on the geolocation metadata. Other embodiments are provided as well.

Abstract: Digital watermark methods for encoding auxiliary data into a host signal are used to authenticate physical and electronic objects. In one implementation, an identification document includes electronic circuitry. The electronic circuitry includes an image of an authorized bearer of the identification document. The image includes first digital watermarking having a plural-bit identifier. In some cases, the identification document includes a printed image of the authorized bearer of the identification document. The printed image includes second digital watermarking therein. The first digital watermarking and the second digital watermarking can be cross-correlated for authentication of the identification document.

Abstract: The present invention relates to systems and methods for managing images and related information. In one implementation, geographic information system (GIS) layer information is registered or aligned to an image using digital watermark information embedded within the image.

Abstract: The ability to remove a watermark from an encoded image opens the possibility of various novel applications. Several such applications are detailed. One employs a reversible watermark in conjunction with a second (robust) watermark. In this arrangement, the payload of the reversible watermark conveys information about the robust watermark (e.g., encoding parameters, or an error signal), permitting removal of the robust watermark from an uncorrupted encoded image. By such arrangements, the encoded image can be fully restored to its pristine, unencoded state even if several different watermarks have been applied.

Abstract: A map depicts a plurality of different locations. Steganographic encoding is embebbed in first and second map areas. Steganographic encoding in each area conveys an identifier that is associated with its respective map area. Different encoded identifiers are used to link to information pertaining various different locations depicted in the map.

Abstract: Digital watermarking technology is used in conjunction with map data, such as is acquired by satellite and other aerial sensors. The watermarks are used to track metadata, provide serialization and forensic tracking, help auto-correlate image data, and quilt together related imagery. One aspect of the present invention contemplates that incoming imagery is automatically geo-referenced and combined with previously collected data sets so as to facilitate generation of revised composite maps. Another aspect of the present invention associates geovector information with a photograph via a digital watermark.

Abstract: The present invention provides techniques whereby objects are readily identified. These inventive techniques are ideally suited for traffic monitoring. In one implementation a vehicle is marked with a machine-readable code on an outer, top surface of the vehicle. An elevated or aerial platform captures an image of the vehicle. A detector analyzes the captured image to recover the machine-readable code. The vehicle is identified from such. Traffic congestion can be determined by monitoring the movement of a marked vehicle through the city traffic. In some implementations the machine-readable code comprises an identifier, which is used to interrogate a database for related information.