Abstract: Apparatus, methods and articles of manufacture for determining an operating mode of a recording/playing device are disclosed. An example apparatus includes an extractor to extract signatures associated with a first signal associated with a tuner that is to tune to a program signal, a second signal associated with a recording/playing device that is to at least one of record and play a program, and a third signal associated with a receiver coupled to the recording/playing device. The example apparatus also includes a recording detector to detect a recording signal generated by the recording/playing device during recording of the program to form a recorded program. Also included is a correlator to correlate the first, second, and third signals and a processor to identify the operating mode of the recording/playing device based on detection of the recording signal and correlation of two or more of the first, second, and third signals.

Abstract: Methods and apparatus to enforce a power off state of an audience measurement device during shipping of the device are disclosed herein. An example portable audience measurement device includes a housing, a media detector in the housing to collect media exposure data, and a packaging sensor to receive an audio signal. A packaging detector generates a frequency spectrum of the detected audio signal, determines an energy of a first frequency associated with the generated frequency spectrum, determines an energy of a second frequency higher than the first frequency and associated with the generated frequency spectrum, and compares the difference between the energy of the first frequency and the second frequency to a muffling threshold to determine whether the device is located within a package.

Abstract: A system that incorporates teachings of the present disclosure may include, for example, an apparatus having a processor adapted to receive a message from a portable communication device communicatively coupled to a set-top box presenting a media program and to retrieve from the message a media descriptor associated with the media program. The processor is further adapted to identify according to the media descriptor one or more images of one or more performers commonly presented in the media program, to monitor one or more frames of a live media feed including the media program, and compare the one or more human figures to the one or more images of performers. The processor can also be adapted to recognize a performer from the comparison, to retrieve information associated with the performer, and to transmit the information to the portable communication device. Other embodiments are disclosed.

Abstract: A method of video fingerprinting computes statistics for video frames and forms a fingerprint used to identify the video as a change in the statistics over the video frames. Another method of video fingerprinting computes values representing motion between different portions of the video and forms a fingerprint to identify the video utilizing data associated with at least the values. Yet another method of video fingerprinting computes values associated with luminance for a first video portion, computes values associated with luminance for a second video portion, determines changes in luminance between the first video portion and the second video portion, and forms a fingerprint to identify the video based at least in part on data associated with the changes.

Abstract: Set top box logs are received from a television provider and processed to identify channel tunes and channel tune times. The channel tunes and channel tune times of the log data can be compared to expected air times of television advertisements on channels, and an impression values, e.g., projected viewers, can be generated for each television advertisement.

Abstract: A linear transformation matrix calculating apparatus linearly transforms a plurality of dictionary subspaces which belong to respective categories by a linear transformation matrix respectively, selects a plurality of sets of two dictionary subspaces from the plurality of linearly transformed dictionary subspaces, calculates a loss function using similarities among the selected sets of dictionary subspaces respectively, calculates a differential parameter obtained by differentiating the loss function by the linear transformation matrix, calculates a new linear transformation matrix from the differential parameter and the linear transformation matrix by Deepest Descent Method, and updates the new linear transformation matrix as the linear transformation matrix used in the linear transformation unit.

Abstract: The present invention relates generally to fingerprinting, e.g., a reduced-bit representation or other identifier of a media signal (e.g., audio, video or still images). One method recites: receiving a partial fingerprint of a media signal, wherein the partial fingerprint is derived from the media signal itself, the partial fingerprint being computed a first location; processing the partial fingerprint to obtain a more refined fingerprint, relative to the partial fingerprint, the act of processing occurring at a second location that is remote from the first location; and based at least in part of the refined fingerprint, identifying the media signal or information associated with the media signal.

Abstract: A method for decomposing a target circuit pattern containing features to be imaged into multiple patterns. The process includes the steps of separating the features to be printed into a first pattern and a second pattern; performing a first optical proximity correction process on the first pattern and the second pattern; determining an imaging performance of the first pattern and the second pattern; determining a first error between the first pattern and the imaging performance of the first pattern, and a second error between the second pattern and the imaging performance of said second pattern; utilizing the first error to adjust the first pattern to generate a modified first pattern; utilizing the second error to adjust the second pattern to generate a modified second pattern; and applying a second optical proximity correction process to the modified first pattern and the modified second pattern.

Abstract: Methods and apparatus to identify media content using temporal signal characteristics are disclosed. An example method to identify media content includes receiving a reference signal corresponding to known media content and generating a reference signature based on the reference signal. The method further includes generating a plurality of sums based on peaks in the media signal and identifying one or more signal peaks based on the generated sums. The method then generates a second signature based on a plurality of normalized curve features, wherein each normalized curve feature corresponds to a signal peak at the temporal location of the signal peak, and determines whether the media signal corresponds to the reference signal based a comparison of the reference signature and the second signature.

Abstract: Methods and apparatus to monitor audio/visual content from various sources are disclosed. An example method to monitor a media content presentation comprises determining whether an audio signal is muted based on whether a number of zero crossings exceeds a threshold, and based on whether the audio signal is determined to be muted, using the audio signal to at least one of determine a source of the media content presentation or determine a special operating mode of the source of the media content presentation. Another example method to monitor a media content presentation comprises determining the source of the media content presentation based on whether the audio signal is determined to be compressed. Yet another example method to monitor a media content presentation comprises determining the source of the media content presentation based on whether the video signal is determined to be compressed.

Abstract: The invention concerns a method for computing a fingerprint of a video sequence. The method comprises the steps of—Computation of a visual digest for each frame of the video, —Computation of the distance between the visual digest of each frame of the video in order to detect shots, —Detection, for each detected shot of the video, of a frame, called stable frame, having the smallest content variation of the shot, —Calculation of a local fingerprint for said stable frame.

Abstract: A method of identifying a target synchronization point pair including a source synchronization point corresponding to a source end and a destination synchronization point corresponding to a destination end is provided. The method includes receiving a source scan-line image corresponding to a first video source from the source end; selecting at least a comparing frame out of the source scan-line image; providing a destination scan-line image corresponding to a second video source at the destination end; and determining the target synchronization point pair by comparing the comparing frame and the destination scan-line image.

Abstract: Methods and apparatus for nonintrusive monitoring of web browser usage are disclosed. An example method for monitoring web browsing disclosed herein comprises obtaining a video signal from a video output of a device implementing a web browser, processing a video image obtained from the video signal to identify a region of the video image displaying at least a portion of the web browser, determining textual information displayed by the web browser in the identified region of the video image, and using the textual information to record usage of the web browser.

Abstract: Reporting data related to content processing devices, e.g., television devices, are processed to identify channel tunes and corresponding tune times of the content processing devices. Automatically generated channel tunes based on the corresponding tune times are identified. Content items that are aired during a time period defined by the corresponding tune times can be adjusted.

Abstract: A method and apparatus for storing a broadcast program are provided. The apparatus includes: a signal processing unit which generates an audio/video (A/V) file, an application file, and a first electronic program guide (EPG) file by appropriately processing a plurality of A/V signals, application information, and EPG information, respectively, which are included in an input broadcast program transport stream; a synchronization unit which receives the A/V file, the application file, and the first EPG file from the signal processing unit, generates storage information for the A/V file and storage information for the application file, and converts the first EPG file into a second EPG file comprising the storage information for the A/V file and the storage information for the application file; and a storage unit which stores the A/V file, the application file, and the second EPG file.

Abstract: Methods and apparatus to detect an internally generated signal mode of a local media playback device are disclosed. A disclosed method comprises tuning a harmonic frequency of a chrominance signal output by a local media playback device, and determining that the local media playback device is in an internally generated signal mode if the measured harmonic frequency exceeds a predetermined threshold.

Abstract: A pattern recognition method comprises steps of inputting a pattern of a recognition object performing feature extraction from the input pattern to generate a feature vector, increasing the number of quantization in an order from quantization number 1 or quantization number 2 to calculate a quantization threshold of each of the quantization number, wherein the quantization threshold of quantization number (n+1) using a quantization threshold of quantization number n (n>=1) is calculated and a quantization function having a quantization threshold corresponding to quantization number S (S>n) is generated, quantizing each component of the feature vector of the input pattern using the quantization function to generate an input quantization feature vector having each of the quantized component, storing a dictionary feature vector of the recognition object, or a quantized dictionary feature vector in which each component of the dictionary feature vector of the pattern of a recognition object is quantized; cal

Abstract: Digital video signature apparatus and methods for use with video program identification systems are disclosed. The example apparatus and methods generate a signature associated with a video program. An example system includes a frame scanner to scan video frames associated with the video program. The frame scanner is to select a video frame based on a number of intra-coded macro blocks within the video frame. The example system also includes an intra-coded macro block extractor to extract intra-coded macro blocks from the video frame and a scaled image extractor to extract a scaled image from the intra-coded macro blocks. A signature generator is also included in the example system to calculate a plurality of centroids associated with video frame based on the scaled image and to form the signature based on the plurality of centroids.

Abstract: Methods and apparatus for identifying audio/video content using temporal characteristics of a signal are disclosed. The disclosed apparatus and methods receive a signature associated with audio/video content presented at a monitored site, wherein the signature is based on a plurality of time intervals associated with audio features of the audio/video content presented at the monitored site and identify the audio/video content presented at the monitored site based on the received signature.

Abstract: Methods and apparatus for characterizing media are described. In one example, a method of characterizing media includes capturing a block of audio; converting at least a portion of the block of audio into a frequency domain representation including a plurality of complex-valued frequency components; defining a band of complex-valued frequency components for consideration; determining a decision metric using the band of complex-valued frequency components; and determining a signature bit based on a value of the decision metric. Other examples are shown and described.

Abstract: A method and system for performing document image correction using a document reader is disclosed. The method includes generating a document image representative of a document having a deformation; decoding an optical pattern embedded in the document from the document image to determine an optical signature for the document; receiving document classification data associated with the optical signature; and applying an image correction technique to the document image based on the document classification data to generate a corrected document image. A document capable of being read by a document reader is also disclosed. The document includes a substrate and an optical pattern embedded on the substrate. The optical pattern is part of a background pattern printed on the substrate. The optical pattern defines an optical signature unique to the particular class of document and is associated with document classification data for the document.

Abstract: Portable audience measurement architectures and methods for portable audience measurement are disclosed. A disclosed system contains a plurality of portable measurement devices configured to collect audience measurement data from media devices, a plurality of data collection servers configured to collect audience measurement data from the plurality of portable measurement devices, and a central data processing server. A portable measurement device establishes a communication link with a data collection server in a peer-to-peer manner and transfers the collected audience measurement data to the data collection server. Because the portable measurement device is not dedicated to a particular local data collection server, the portable measurement device periodically or a periodically broadcasts a message attempting to find a data collection server with which to establish a communication link.

Abstract: Methods and apparatus for detecting on-screen media sources are disclosed. An example method includes monitoring a region of interest of a video signal for a first image, comparing the first image to a stored image, and confirming the media device change when the stored image differs from the first image and is associated with a secondary criterion.

Abstract: Digital video signature apparatus and methods for use with video program identification systems are disclosed. The disclosed apparatus and methods identify a video program using a sequence of signatures. Each of the signatures includes a set of centroids corresponding to one of a plurality of frames of the video program. The apparatus and methods compare the sequence of signatures to a set of reference sequences of signatures and identify the video program based on the comparison of the sequence of signatures to the set of reference sequences of signatures.

Abstract: Methods and apparatus to detect blank images in a digital video broadcast signal are disclosed. An example method of detecting a blank image includes analyzing DC values of luminance blocks associated with a frame to determine a number of the luminance blocks having substantially the same DC value; and identifying the frame as a blank image if the number exceeds a predetermined threshold.

Abstract: A system and method is disclosed for detecting distribution of multimedia content. The volume level of data traffic is monitored for a plurality of users to select any users with high-bandwidth usage. The time of day and the day of the week may be considered when determining whether a user is a high-bandwidth user. Upon selecting a user as one with high-bandwidth usage, such user may be subject to packet inspections of data traffic streams. In some embodiments, content identification parameters or watermarks are added to one or more packets in a data traffic stream carrying multimedia content.

Abstract: A detection apparatus includes a tuner tuned to the program and a meter coupled to the tuner and arranged to detect content ancillary information from the program tuned by the tuner. The content ancillary information may be a media link, closed captioning information, or the like. The meter may also be arranged to extract a broadcast signature from the program. A comparator compares the broadcast signature to a reference signature selected from a library of reference signatures based upon the content ancillary information. Broadcast signatures from unknown programs may be clustered at least partially on the basis of the content ancillary information.

Abstract: A method of determining whether live media content or time-shifted media content is received at a communication device is presented. In the method, attribute information concerning media content received at a communication device at a specific time is received. Also received is schedule information including an identity of media content carried at the specific time over a channel identified in the attribute information. The media content identity from the attribute information is compared with the media content identity from the schedule information. The received media content is determined to be live media content if the media content identity from the attribute information agrees with the media content identity from the schedule information. The received media content is determined to be time-shifted media content if the media content identity from the attribute information does not agree with the media content identity from the schedule information.

Abstract: Methods and apparatus to adjust signature matching results for audience measurement are disclosed. An example method to adjust a signature matching result associated with monitoring a media content presentation disclosed herein comprises obtaining a monitored signature representative of the monitored media content presentation from a monitoring device, obtaining an environmental characteristic associated with the monitored signature from the monitoring device, and adjusting the signature matching result using an adjustment value when the monitored signature is determined to match a reference signature representative of reference media content, the adjustment value selected from a plurality of adjustment values based on the matched reference signature and the environmental characteristic.

Abstract: A viewing surveillance system which make it possible to carry out the viewing surveillance independently from the broadcasting form like analog broadcasting or digital broadcasting. The viewing surveillance system also make it possible to carry out the viewing surveillance without any restriction set to viewers or any burden to the broadcast stations. The image feature data generating unit 12 receives a picture signal from the image viewing terminal 50, and generates the image feature data which represents a feature of the image from the picture signal. The image information transmitting unit 13 transmits the image feature data generated by the image feature data generating unit 12 to the viewing surveillance server 2. On the other hand, the image feature data generating units 21a to 21c also generates the image feature data based on the broadcasted programs and stores the image feature data in the program image feature data storing unit 22.

Abstract: A method and system for the automatic identification of audio, video, multimedia, and/or data recordings based on immutable characteristics of these works. The invention does not require the insertion of identifying codes or signals into the recording. This allows the system to be used to identify existing recordings that have not been through a coding process at the time that they were generated. Instead, each work to be recognized is “played” into the system where it is subjected to an automatic signal analysis process that locates salient features and computes a statistical representation of these properties. These features are then stored as patterns for later recognition of live input signal streams. A different set of features is derived for each audio or video work to be identified and stored. During real-time monitoring of a signal stream, a similar automatic signal analysis process is carried out, and many features are computed for comparison with the patterns stored in a large feature database.

Abstract: Methods and systems are provided for gathering research data. Frequency domain data is received or produced, a signature is extracted from the frequency domain data and an ancillary code is read from the frequency domain data.

Abstract: An electronic device is provided comprising a multimedia play unit and a processor. The processor receives a multimedia sequence, acquires a first bitrate of a first frame header from the received multimedia sequence, predicts a first length of a first frame comprising the first frame header by a formula employing at least parameters comprising the first bitrate and a proportion of a second length to a second bitrate of a second frame header prior to the first frame header, and directs the multimedia play unit to play frame data of the first frame according to the predicted first length of the first frame.

Abstract: Display device ON/OFF detection methods and apparatus are disclosed. An example method disclosed herein to determine whether a presentation device is ON or OFF comprises determining a plurality of metrics based on monitoring at least one output of the presentation device, wherein each metric in the plurality of metrics comprises a decision indicating an operating state of the presentation device, and combining the plurality of metrics to determine whether the presentation device is one of ON or OFF, wherein combining the plurality of metrics comprises at least one of weighting the plurality of metrics or determining a majority vote of the plurality of metrics.

Abstract: A method and system for the automatic identification of audio, video, multimedia, and/or data recordings based on immutable characteristics of these works. The invention does not require the insertion of identifying codes or signals into the recording. This allows the system to be used to identify existing recordings that have not been through a coding process at the time that they were generated. Instead, each work to be recognized is “played” into the system where it is subjected to an automatic signal analysis process that locates salient features and computes a statistical representation of these properties. These features are then stored as patterns for later recognition of live input signal streams. A different set of features is derived for each audio or video work to be identified and stored. During real-time monitoring of a signal stream, a similar automatic signal analysis process is carried out, and many features are computed for comparison with the patterns stored in a large feature database.

Abstract: Systems and methods for providing enhanced metadata to a user. Systems and methods can include extraction of data from metadata and searching for related metadata based upon the the extracted data.

Abstract: A method and an automated system of identifying and editing commercials are provided. The audio signals of broadcasted television or audio content is received and processed to generate voice print profiles of the actors of a particular show. The voice print profiles are stored in a system database and are periodically updated. The current voice print profile is matched with a previously identified voice print profile to identify commercials. The commercials are edited and the user views the television content without the undesired content.

Abstract: Set top box logs are received from a television provider and processed to compensate for broadcast latency and generate normalized log data, e.g., log data that are indexed to a relative time. Channel tunes and the channel tune times of the normalized log data can be compared to expected air times of television advertisements on channels, and an impression values, e.g., projected viewers, can be generated for each television advertisement.

Abstract: Digital video signature apparatus and methods for use with video program identification systems are disclosed. The disclosed apparatus and methods identify a video program using a sequence of signatures. Each of the signatures includes a set of centroids corresponding to one of a plurality of frames of the video program. The apparatus and methods compare the sequence of signatures to a set of reference sequences of signatures and identify the video program based on the comparison of the sequence of signatures to the set of reference sequences of signatures.

Abstract: The present invention relates to a recommending system that recommends content so as to keep constant network traffic between a user terminal and a server. The recommending system includes a user terminal, a content server that transmits content prestored in a storage device to the user terminal, and a recommending server that transmits recommendation data, which are connected via a network. The recommending server includes a communications unit that transmits the recommendation data to the user terminal, the recommendation data containing an identifier of provided content and a time, at which the content server starts providing the content to the user terminal, in correspondence with the identifier of the provided content. The user terminal includes a download unit that transmits the content request containing the identifier of the provided content to the content server at the time in correspondence with the identifier of the provided content in the recommendation data.

Abstract: For digital media, audience evaluation is performed as a result of transmitter-receiver interaction similar to a lottery game. The transmitter provides receivers with a preliminary audience estimate and a “winning” number, both placed in control packets multiplexed with a media stream. Each receiver generates a random number within a range of numbers proportional to the audience estimate and if the winning number is generated, the receiver sends a “claim” back to the transmitter over a return path. The transmitter increases or decreases the audience estimate placed in control packets if the number of “winners” is statistically greater or lesser than theoretically predicted for correct estimates until the number of winners becomes as predicted. Reducing the volume of data transmitted over the return path and keeping the volume independent from audience size, the system prevents the return pass capacity overload and provides an accurate measurement of any audience no matter how large or small it is.

Abstract: Digital video signature apparatus and methods for use with video program identification systems are disclosed. The disclosed apparatus and methods identify a video program using a sequence of signatures. Each of the signatures includes a set of centroids corresponding to one of a plurality of frames of the video program. The apparatus and methods compare the sequence of signatures to a set of reference sequences of signatures and identify the video program based on the comparison of the sequence of signatures to the set of reference sequences of signatures.

Abstract: Methods, apparatus, and articles of manufacture for media monitoring are disclosed. In particular, the example methods, apparatus, and articles of manufacture generate digital spectral signatures for use in identifying media information. Initially, a frame of media samples is obtained. A first frequency component having a first spectral power and a second frequency component having a second spectral power are identified by performing a spectral transform operation on the frame of media samples. A descriptor of the first frame of media samples is determined based on a comparison of the first spectral power and the second spectral power. A first signature is then generated based on the descriptor.

Abstract: Methods and apparatus to export tuning data collected in a receiving device are disclosed. An example method of collecting audience measurement data comprises collecting tuning data within a receiving device, and modulating an LED associated with the receiving device to export the collected tuning data from the receiving device.

Abstract: A method and apparatus for generating discriminant functions for distinguishing obscene videos by using visual features of video data, and a method and apparatus for determining whether videos are obscene by using the generated discriminant functions, are provided.

Abstract: The present invention discloses an apparatus and a method for calculating audience rating on a designated content based on user history record for an interactive television, in which the interactive television is able to provide user-oriented services by receiving the consumption type and the consumption behavior record information in the user history recorder of the interactive television; storing information on the user's action on the content and information on the content in the user history record; transferring the user record information to the content provider every designated cycle; and calculating the user's audience rating on each section in the designated content based on the analysis on the user record information.

Abstract: A detection apparatus includes a tuner tuned to the program and a meter coupled to the tuner and arranged to detect content ancillary information from the program tuned by the tuner. The content ancillary information may be a media link, closed captioning information, or the like. The meter may also be arranged to extract a broadcast signature from the program. A comparator compares the broadcast signature to a reference signature selected from a library of reference signatures based upon the content ancillary information. Broadcast signatures from unknown programs may be clustered at least partially on the basis of the content ancillary information.

Abstract: A system for automatically monitoring the viewing activities of television signals, comprising a measurement device, in which the television signals are adapted to be communicated to the measurement device and the TV set, making the measurement device receive the same signals as the TV set; the measurement device is adapted to extract a fingerprint data from the television signals displayed to the viewers, making the measurement device measures the same video signals as those being seen by the viewers; a data center to which the fingerprint data is transferred; and a fingerprint matcher to which the television signals which the viewers are selected to watch are sent to be monitored through the measurement device. The system according to the present invention does not require any change to the other devices already in place before the measurement device is introduced into the connections.

Abstract: Methods and apparatus to detect an internally generated signal mode of a local media playback device are disclosed. A disclosed method comprises tuning a harmonic frequency of a chrominance signal output by a local media playback device, and determining that the local media playback device is in an internally generated signal mode if the measured harmonic frequency exceeds a predetermined threshold.

Abstract: Method and apparatus for identifying broadcast digital audio signals include structure and/or function whereby the digital audio signal is provided to processing structure which is configured to (i) identify a program-identifying code in the received digital audio signal, (ii) identify a program-identifying code in a decompressed received digital audio signal, (iii) identify a feature signature in the received digital audio signal, and (iv) identify a feature signature in the decompressed received digital audio signal. Preferably, such processing structure is disposed in a dwelling or a monitoring site in an audience measurement system, such as the Nielsen TV ratings system.