Koninklijke Philips Corporation N.v.

Civolution B.v.

Gracenote, Inc.

Koninklijke Phillips Electronics N.v.

Teletrax B.v.

Nagravision S.a.

Koninklijke Philips Electronics N.v.

Jaap Andre Haitsma

Antonius Adrianus Cornelis Maria Kalker

Antonius A C M Kalker

Alphons Antonius Maria Lambertus Bruekers

Minne Van Der Veen

Job Cornelis Oostveen

Constant Paul Marie Jozef Baggen

Martijn Maas

Adrianus J M Denissen

Geert F G Depovere

Antonius Adriaan Maria Staring

Johan P M G Linnartz

Marc Joseph Rita Op De Beeck

Mehmet Utku Celik

Gerrit Cornelis Langelaar

Maurice J J J-b Maes

Gijsbrecht C Wirtz

Marc J R Op De Beeck

Alex Dick Terpstra

Adranius J M Denissen

Johan Paul Marie Gerald Linnartz

Steven Marco Schimmel

The problem is solved by a method for broadcasting a broadcast signal, comprising generating an information signal having in time a first content up to a certain time and a second content after this time. The information signal is broadcast as a broadcast signal via a first communication link. At least one first feature is being provided with respect to the second content, for example an advertisement. The second content is detected in the information signal using the at least one first feature. On detection of the second content in the information signal at least one second feature is extracted from the first content in the information signal preceding the second content. The at least one second feature is sent to a user device using a second communication link, different from the first communication link, the second communication link being faster than the first communication link.

Broadcasting an information signal having special content for triggering an appropriate action in a user device

Client terminals report an easy-to-calculate identifier such as the Internet URL or a cryptographic hash of the content to a server. The server collects and counts the reported identifiers so as to obtain preliminary statistics. By aggregating these reported identifiers into the preliminary statistics, identifiers are revealed that are likely popular content. The server selects one or more identifiers from the preliminary statistics and makes these available to at least a subset of clients. The clients that obtain these one or more identifiers then access content and compute the easy-to-calculate identifiers as usual. If the computed identifier matches one of the identifiers obtained from the server, the client will additionally extract a watermarked identifier or compute a digital fingerprint of the content in question and report this to the server. The server then uses the received identifier or fingerprint to create final statistics by aggregating the preliminary statistics.

Generating statistics of popular content

A video watermarking scheme is disclosed, which is designed for the digital cinema format, as it will be used on large projector screens in theaters. The watermark is designed in such a way that it has minimal impact on the video quality, but is still detectable after capture with a handheld camera and conversion to, for instance, VHS, CD-Video or DVD format. The proposed watermarking system only exploits the temporal axis. This makes it invulnerable to geometrical distortions generally caused by such a way of capturing. The watermark is embedded by modulating a global property of the frames (e.g. the mean luminance) in accordance with the samples of the watermark. The embedding depth is preferably locally adapted within each frame to local statistics of the respective image. Watermark detection is performed by correlating the watermark sequence with extracted mean luminance values of a sequence of frames.

Embedding and detection of watermark in a motion image signal

Hashes are short summaries or signatures of data files which can be used to identify the file. The disclosed method generates robust hashes for multimedia content, for example, audio clips. The audio clip is divided into successive (preferably overlapping) frames. For each frame, the frequency spectrum is divided into bands. A robust property of each band (e.g. energy) is computed and represented by a respective hash bit. An audio clip is thus represented by a concatenation of binary hash words, one for each frame. To identify a possibly compressed audio signal, a block of hash words derived therefrom is matched by a computer with a large database. Such matching strategies are also disclosed. In an advantageous embodiment, the extraction process also provides information as to which of the hash bits are the least reliable. Flipping these bits considerably improves the speed and performance of the matching process.

Generating and matching hashes of multimedia content

Disclosed is a method of adjusting a supplementary data signal (wm(n)) to be embedded in an information signal (x(n)), for example an audio signal. The method comprises the steps of determining () a position where a predetermined property of the information signal exceeds a predetermined threshold, e.g. an attack position, and suppressing () the supplementary data signal in a predetermined neighbourhood of the determined position.

Embedding supplementary data in an information signal

Hashes are short summaries or signatures of data files which can be used to identify the file. Hashing multimedia content (audio, video, images) is difficult because the hash of original content and processed (e.g. compressed) content may differ significantly. The disclosed method generates robust hashes for multimedia content, for example, audio clips. The audio clip is divided () into successive (preferably overlapping) frames. For each frame, the frequency spectrum is divided () into bands. A robust property of each band (e.g. energy) is computed () and represented () by a respective hash bit. An audio clip is thus represented by a concatenation of binary hash words, one for each frame. To identify a possibly compressed audio signal, a block of hash words derived therefrom is matched by a computer () with a large database (). Such matching strategies are also disclosed. In an advantageous embodiment, the extraction process also provides information () as to which of the hash bits are the least reliable. Flipping these bits considerably improves the speed and performance of the matching process.

A method of updating a database () comprising a fingerprint of and an associated set of metadata for each of a number of multimedia objects, A multimedia object and a set of metadata for the multimedia object is downloaded from a file sharing client (-). A fingerprint is computed from the multimedia object, and the computed fingerprint and the obtained set of metadata are included in the database (). The database () can be maintained by a central server (), or be maintained in a distributed fashion by servers () running on the file sharing clients (-). The database () in this way accumulates plural sets of metadata associated with one particular fingerprint. When a sufficient number of sets has been collected, a definite set can be determined using filtering techniques.

Fingerprint database updating method, client and server

A robust fingerprinting system is disclosed. Such a system can recognize unknown multimedia content (U(t)) by extracting a fingerprint (a series of hash words) from said content, and searching a resembling fingerprint in a database in which fingerprints of a plurality of known contents (K(t)) are stored. In order to more efficiently store the fingerprints in the database and to speed up the search, the hash words (H(n)) of known signals (K(t)) are sub-sampled () by a factor M prior to storage in the database (). The hash words (H(n)) of unknown signals (U(t)) are divided () into M interleaved sub-series (H(n) . . . HM&#x2212;1(n)). The interleaved sub-series are selectively () applied to the database () under the control of a computer (). If only one of the sub-series sufficiently matches a stored fingerprint, the signal is identified.

Efficient storage of fingerprints

A method and arrangement for detecting a watermark embedded in an MPEG compressed signal includes a conventional MPEG decoder stripped to such an extent that a modified baseband video signal suitable for watermark detection is obtained. A plurality of pictures with the embedded watermark is accumulated () in the transform domain, and the inverse DCT () is applied to the accumulated result. Conventional watermark detection () is then applied to the accumulated plurality of pictures in the spatial domain.

Detection of a watermark in a compressed video signal

A digital media recorder and a method of controlling such are provided. During attempts to copy media content, sub-sequences are extracted from an input media sequence. A digital fingerprint of the sub-sequence is calculated and compared with at least one first reference fingerprint from a database. The outcome of the comparison determines the action to take in the further processing. Recording of the input media sequence on a media carrier is either allowed or obstructed, e.g. disallowed. In the case recording of the sequence is allowed, the database is updated with information that the digital media sequence has been recorded.

Copy control using digital speed bumps

methods of embedding and detecting a watermark in an information signal (x(n), y'(n)) which are robust against sampling rate conversions of the watermarked signal (y(n)) adapts frame lengths used by an embedder and the detector, respectively, so as to preserve a constant ratio between the respective sampling rate and frame length. The frame lengths may be calculated from a greatest common divisor of a set of sampling rates providing watermarks which are robust against sampling rate conversions between any sampling rates of the set of sampling rates.

Watermarking

An improved method and arrangement for detecting a watermark in an information (e.g. image or video) signal are disclosed. The detection is more reliable and less vulnerable to image processing by partitioning the image into a sequence of blocks having a predetermined size, accumulating the blocks, computing a value indicative of the correlation of the accumulated blocks and the watermark having the predetermined size, and detecting whether the correlation value is larger than a predetermined threshold.

Watermark detection

The invention relates to a method of checking the correct operation of a signal transformation wherein a input signal is transformed into an output signal. The method comprises: deriving a first robust feature from the input signal; deriving a second robust feature from the output signal; comparing said first and second robust features; in case of sufficient sumilarity, concluding a correct operation of said signal transformation, and in case of insufficient sumilarity, concluding a false operation of said signal transformation. In a special embodiment, the method is applied wherein the first robust feature is embedded in the input signal through watermark technology, the thus obtained signal being transmitted to a receiver so as to retrieve an output signal corresponding to said input signal.

Growing community of inventors

Eindhoven, Netherlands

Jaap Andre Haitsma