The technology detailed herein spans a range of subject matter, including identifying audio/video entertainment content.
Certain implementations of the present technology make use of Amazon's Mechanical Turk service. Amazon's Turk web site explains:
All software developers need to do is write normal code. The pseudo code below illustrates how simple this can be.
More information about Amazon's Mechanical Turk service is provided in the attached Appendix A (Amazon Mechanical Turk Developer Guide, 2006, 165 pp., API Version 10-31-2006).
The Mechanical Turk service may be regarded as a structured implementation of a technology commonly termed “crowdsourcing”—employing a group of outsiders to perform a task. Wikipedia explains:
While not a new idea, crowdsourcing is becoming mainstream. Open source projects are a form of crowdsourcing that has existed for years. People who may not know one another work together online to create complex software such as the Linux kernel, and the Firefox browser. In recent years internet technology has evolved to allow non-technical people to participate in online projects. Just as important, crowdsourcing presumes that a large number of enthusiasts can outperform a small group of experienced professionals.
Advantages
The main advantages of crowdsourcing is that innovative ideas can be explored at relatively little cost. Furthermore, it also helps reduce costs. For example if customers reject a particular design, it can easily be scrapped. Though disappointing, this is far less expensive than developing high volumes of a product that no one wants. Crowdsourcing is also related to terms like Collective Customer Commitment (CCC) and Mass Customisation. Collective Customer Commitment (CCC) involves integrating customers into innovation processes. It helps companies exploit a pool of talent and ideas and it also helps firms avoid product flops. Mass Customisation is somewhat similar to collective customer commitment; however, it also helps companies avoid making risky decisions about what components to prefabricate and thus avoids spending for products which may not be marketable later.
Types of Crowdsourced Work
The Rise of Crowdsourcing, Wired June 2006.
Crowdsourcing: Consumers as Creators, BusinessWeek July 2006.
The following text presents a simplified, incomplete summary in order to provide an orientation to certain aspects of the disclosed subject matter. This Summary is not an extensive overview. It is not intended to identify key/critical elements or to delineate the scope of the claimed subject matter. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that follows.
In accordance with certain embodiments of the present technology, Amazon's Mechanical Turk system, or similar crowdsourcing arrangements, are employed to match a first item of visual or audio entertainment content to a counterpart in a universe of such items.
For example, consider a user social networking site such as YouTube (now Google) that distributes “user generated content” (e.g., video files), and employs fingerprinting to recognize media content that should not be distributed. The site may check a video file at the time of its uploading with a fingerprint recognition system (e.g., of the sort offered by Audible Magic, or Gracenote). If no clear match is identified, the video may be indexed and stored on YouTube's servers, available for public downloading. Meanwhile, the content can be queued for review by one or more crowdsource reviewers. They may recognize it as a clip from the old TV sitcom “I Love Lucy”—perhaps digitally rotated 3 degrees to avoid fingerprint detection. This tentative identification is returned to YouTube from the API call. YouTube can check the returning metadata against a title list of works that should not be distributed (e.g., per the request of copyright owners), and may discover that “I Love Lucy” clips should not be distributed. It can then remove the content from public distribution. Additionally, the fingerprint database can be updated with the fingerprint of the rotated version of the I Love Lucy clip, allowing it to be immediately recognized the next time it is encountered. The foregoing and other examples, features and advantages of the present technology will be more apparent from the following Detailed Description.
One use of the Mechanical Turk service (and similar crowdsourcing technologies) is in connection with computationally difficult tasks, such as identification of audio, video and imagery content. These tasks are sometimes addressed by so-called “fingerprint” technology, which seeks to generate a “robust hash” of content (e.g., distilling a digital file of the content down to perceptually relevant features), and then compare the thus-obtained fingerprint against a database of reference fingerprints computed from known pieces of content, to identify a “best” match. Such technology is detailed, e.g., in Haitsma, et al, “A Highly Robust Audio Fingerprinting System,” Proc. Intl Conf on Music Information Retrieval, 2002; Cano et al, “A Review of Audio Fingerprinting,” Journal of VLSI Signal Processing, 41, 271, 272, 2005; Kalker et al, “Robust Identification of Audio Using Watermarking and Fingerprinting,” in Multimedia Security Handbook, CRC Press, 2005, and in patent documents WO02/065782, US20060075237, US20050259819, and US20050141707.
A related technology is facial recognition—matching an unknown face to a reference database of facial images. Again, each of the faces is distilled down to a characteristic set of features, and a match is sought between an unknown feature set, and feature sets corresponding to reference images. (The feature set may comprise eigenvectors or shape primitives.) Patent documents particularly concerned with such technology include US20020031253, U.S. Pat. No. 6,292,575, U.S. Pat. No. 6,301,370, U.S. Pat. No. 6,430,306, U.S. Pat. No. 6,466,695, and U.S. Pat. No. 6,563,950.
These are examples of technology that relies on “fuzzy” matching. The fingerprint derived from the unknown content often will not exactly match any of the reference fingerprints in the database. Thus, the database must be searched not just for the identical content fingerprint, but also for variants.
Expanding the search to include variants hugely complicates—and slows—the database search task. To make the search tractable, one approach is to prune the database—identifying excerpts thereof that are believed to be relatively likely to have a match, and limiting the search to those excerpts (or, similarly, identifying excerpts that are believed relatively unlikely to have a match, and not searching those excerpts).
The database search may locate several reference fingerprints that are similar to the fingerprint of the unknown content. The identification process then seeks to identify a “best” match, using various algorithms.
Such content identification systems can be improved by injecting a human into the process—by the Mechanical Turk service or similar systems.
In one particular arrangement, the content identification system makes an assessment of the results of its search, e.g., by a score. A score of 100 may correspond to a perfect match between the unknown fingerprint and a reference fingerprint. Lower scores may correspond to successively less correspondence. (At some lower score, Sx, (perhaps 60) the system may decide that there is no suitable match, and a “no-match” result is returned, with no identification made.)
Above some threshold score, Sy, (perhaps 70) the system may be sufficiently confident of the result that no human intervention is necessary. At scores below Sy, the system may make a call through the Mechanical Turk service for assistance.
The Mechanical Turk can be presented the unknown content (or an excerpt thereof), and some reference content, and asked to make a comparison. (The reference content may be stored in the fingerprint database, or may be readily obtainable through use of a link stored in the reference database.)
A single item of reference content can be provided for comparison with the unknown content, or several items of reference content can be provided. (Again, excerpts may be used instead of the complete content objects. Depending on the application, the content might be processed before sending to the crowdsource engine, e.g., removing metadata (such as personally identifiable information: name, driver license number, etc.) that is printed on, or conveyed with, the file.)
The requested comparison can take different forms. The service can be asked simply whether two items appear to match. Or it can be asked to identify the best of several possible matches (or indicate that none appears to match). Or it can be asked to give a relative match score (e.g., 0-100) between the unknown content and one or more items reference content.
In many embodiments, a query is referred to several different humans (e.g., 2-50) through the Mechanical Turk service, and the returned results are examined for consensus on a particular answer. In some queries (e.g., does Content A match Content B? Or is Content A a better match to Content C?), a “vote” may be taken. A threshold of consensus (e.g., 51%, 75%, 90%, 100%) may be required in order for the service response to be given weight in the final analysis. Likewise, in queries that ask the humans to provide a subjective score, the scores returned from plural such calls may be combined to yield a net result. (The high and/or low and/or outlier scores may be disregarded in computing the net result; weighting can sometimes be employed, as noted below.)
As suggested, the data returned from the Mechanical Turk calls may serve as a biasing factor, e.g., pushing an algorithmically determined output one way or another, to yield a final answer (e.g., a net score). Or the data returned from the Mechanical Turk calls may be treated as a definitive answer—with results from preceding processes disregarded.
Sometimes the database search may reveal several candidate matches, all with comparable scores (which may be above the threshold Sy). Again, one or more calls to the Mechanical Turk service may be invoked to decide which match is the best, from a subjective human standpoint.
Sometimes the Mechanical Turk service can be invoked even in situations where the original confidence score is below the threshold, Sx, which is normally taken as indicating “no match.” Thus, the service can be employed to effectively reduce this threshold—continuing to search for potential matches when the rote database search does not yield any results that appear reliable.
The service can also be invoked to effect database pruning. For example, a database may be organized with several partitions (physical or logical), each containing information of a different class. In a facial recognition database, the data may be segregated by subject gender (i.e., male facial portraits, female facial portraits), and/or by age (15-40, 30-65, 55 and higher—data may sometimes be indexed in two or more classifications), etc. In an image database, the data may be segregated by topical classification (e.g., portrait, sports, news, landscape). In an audio database, the data may be segregated by type (spoken word, music, other). Each classification, in turn, can be further segregated (e.g., “music” may be divided into classical, country, rock, other). And these can be further segregated (e.g., “rock” may be classified by genre, such as soft rock, hard rock, Southern rock; by artist, e.g., Beatles, Rolling Stones, etc).
A call to the Mechanical Turk can be made, passing the unknown content object (or an excerpt thereof) to a human reviewer, soliciting advice on classification. The human can indicate the apparent class to which the object belongs (e.g., is this a male or female face? Is this music classical, country, rock, or other?). Or, the human can indicate one or more classes to which the object does not belong.
With such human advice (which, again, may involve several human reviewers, with a voting or scoring arrangement), the system can focus the database search where a correct match—if any—is more likely to be found (or avoid searching in unproductive database excerpts). This focusing can be done at different times. In one scenario it is done after a rote search is completed, in which the search results yield matches below the desired confidence level of Sy. If the database search space is thereafter restricted by application of human judgment, the search can be conducted again in the limited search space. A more thorough search can be undertaken in the indicated subset(s) of the database. Since a smaller excerpt is being searched, a looser criteria for a “match” might be employed, since the likelihood of false-positive matches is diminished. Thus, for example, the desired confidence level Sy might be reduced from 70 to 65. Or the threshold Sx at which “no match” is concluded, may be reduced from 60 to 55. Alternatively, the focusing can be done before any rote searching is attempted.
The result of such a human-focused search may reveal one or more candidate matches. The Mechanical Turk service may be called a second time, to vet the candidate matches—in the manner discussed above. This is one of several cases in which it may be desirable to cascade Mechanical Turk calls—the subsequent calls benefiting from the former.
In the example just-given, the first Mechanical Turk call aids in pruning the database for subsequent search. The second call aids in assessing the results of that subsequent search. In other arrangements, Mechanical Turk calls of the same sort can be cascaded.
For example, the Mechanical Turk first may be called to identify audio as music/speech/other. A second call may identify music (identified per the first call) as classical/country/rock/other. A third call may identify rock (identified per the second call) as Beatles/Rolling Stones/etc. Here, again, by iterative calling of a crowdsourcing service, a subjective judgment can be made that would be very difficult to achieve otherwise.
In some arrangements, human reviewers are pre-qualified as knowledgeable in a specific domain (e.g., relatively expert in recognizing Beatles music). This qualification can be established by an online examination, which reviewers are invited to take to enable them to take on specific tasks (often at an increased rate of pay). Some queries may be routed only to individuals that are pre-qualified in a particular knowledge domain. In the cascaded example just given, for example, the third call might be routed to one or more users with demonstrated expertise with the Beatles (and, optionally, to one or more users with demonstrated expertise with the Rolling Stones, etc). A positive identification of the unknown content as sounding like the Beatles would be given more relative weight if coming from a human qualified in this knowledge domain. (Such weighting may be taken into account when aggregating results from plural human reviewers. For example, consider an unknown audio clip sent to six reviewers, two with expertise in the Beatles, two with expertise in the Rolling Stones, and two with expertise in the Grateful Dead. Assume the Beatles experts identify it as Beatles music, the Rolling Stones experts identify it as Grateful Dead music, and the Grateful Dead experts identify it as Rolling Stones music. Despite the fact that there are tie votes, and despite the fact that no selection earned a majority of the votes, the content identification service that made these calls and is provided with these results may logically conclude that the music is Beatles.)
Calls to the Mechanical Turk service may request the human to provide metadata relevant to any content reviewed. This can include supposed artist(s), genre, title, subject, date, etc. This information (which may be ancillary to a main request, or may comprise the entirety of the request) can be entered into a database. For example, it can be entered into a fingerprint database—in association with the content reviewed by the human.
Desirably, data gleaned from Mechanical Turk calls are entered into the database, and employed to enrich its data—and enrich information that can be later mined from the database. For example, if unknown content X has a fingerprint Fx, and through the Mechanical Turk service it is determined that this content is a match to reference content Y, with fingerprint Fy, then a corresponding notation can be added to the database, so that a later query on fingerprint Fx (or close variants thereof) will indicate a match to content Y. (E.g., a lookup table initially indexed with a hash of the fingerprint Fx will point to the database record for content Y.)
Calls to outsourcing engines involve a time lag before results are returned. The calling system can generally cope, or be adapted to cope, with such lags.
Consider a user social networking site such as YouTube (now Google) that distributes “user generated content” (e.g., video files), and employs fingerprinting to recognize media content that should not be distributed. The site may check a video file at the time of its uploading with a fingerprint recognition system (e.g., of the sort offered by Audible Magic, or Gracenote). If no clear match is identified, the video may be indexed and stored on YouTube's servers, available for public downloading. Meanwhile, the content can be queued for review by one our more crowdsource reviewers. They may recognize it as a clip from the old TV sitcom “I Love Lucy”—perhaps digitally rotated 3 degrees to avoid fingerprint detection. This tentative identification is returned to YouTube from the API call. YouTube can check the returning metadata against a title list of works that should not be distributed (e.g., per the request of copyright owners), and may discover that “I Love Lucy” clips should not be distributed. It can then remove the content from public distribution. (This generally follows a double-check of the identification by a YouTube employee.) Additionally, the fingerprint database can be updated with the fingerprint of the rotated version of the I Love Lucy clip, allowing it to be immediately recognized the next time it is encountered.
If the content is already being delivered to a user at the moment the determination is made (i.e., the determination that the content should not be distributed publicly), then the delivery can be interrupted. An explanatory message can be provided to the user (e.g., a splash screen presented at the interruption point in the video).
Rotating a video by a few degrees is one of several hacks that can defeat fingerprint identification. (It is axiomatic that introduction of any new content protection technology draws hacker scrutiny. Familiar examples include attacks against Macrovision protection for VHS tapes, and against CSS protection for packaged DVD discs.) If fingerprinting is employed in content protection applications, such as in social networking sites (as outlined above) or peer-to-peer networks, its vulnerability to attack will eventually be determined and exploited.
Each fingerprinting algorithm has particular weaknesses that can be exploited by hackers to defeat same. An example will help illustrate.
A well known fingerprinting algorithm operates by repeatedly analyzing the frequency content of a short excerpt of an audio track (e.g., 0.4 seconds). The method determines the relative energy of this excerpt within 33 narrow frequency bands that logarithmically span the range 300 Hz—2000 Hz. A corresponding 32-bit identifier is then generated from the resulting data. In particular, a frequency band corresponds to a data bit “1” if its energy level is larger than that of the band above, and a “0” if its energy level is lower. (A more complex arrangement can also take variations over time into account, outputting a “1” only if the immediately preceding excerpt also met the same test, i.e., having a band energy greater than the band above.)
Such a 32 bit identifier is computed every hundredth of a second or so, for the immediately preceding 0.4 second excerpt of the audio track, resulting in a large number of “fingerprints.” This series of characteristic fingerprints can be stored in a database entry associated with the track, or only a subset may be stored (e.g., every fourth fingerprint).
When an unknown track is encountered, the same calculation process is repeated. The resulting set of data is then compared against data earlier stored in the database to try and identify a match. (As noted, various strategies can be employed to speed the search over a brute-force search technique, which yields unacceptable search times.)
While the just-described technique is designed for audio identification, a similar arrangement can be used for video. Instead of energies in audio subbands, the algorithm can use average luminances of blocks into which the image is divided as the key perceptual features. Again, a fingerprint can be defined by determining whether the luminance in each block is larger or smaller than the luminance of the preceding block.
The just-reviewed fingerprinting algorithm is particularly detailed in the Haitsma paper, referenced above. Four paragraphs from that paper, further detailing fingerprint extraction, are reproduced below:
Most fingerprint extraction algorithms are based on the following approach. First the audio signal is segmented into frames. For every frame a set of features is computed. Preferably the features are chosen such that they are invariant (at least to a certain degree) to signal degradations. Features that have been proposed are well known audio features such as Fourier coefficients, Mel Frequency Cepstral Coefficients (MFFC), spectral flatness, sharpness, Linear Predictive Coding (LPC) coefficients and others. Also derived quantities such as derivatives, means and variances of audio features are used. Generally the extracted features are mapped into a more compact representation by using classification algorithms, such as Hidden Markov Models, or quantization. The compact representation of a single frame is referred to as a sub-fingerprint. The global fingerprint procedure converts a stream of audio into a stream of sub-fingerprints. One sub-fingerprint usually does not contain sufficient data to identify an audio clip. The basic unit that contains sufficient data to identify an audio clip (and therefore determining the granularity) will be referred to as a fingerprint-block.
The proposed fingerprint extraction scheme is based on this general streaming approach. It extracts 32-bit sub-fingerprints for every interval of 11.6 milliseconds. A fingerprint block consists of 256 subsequent sub-fingerprints, corresponding to a granularity of only 3 seconds. The audio signal is first segmented into overlapping frames. The overlapping frames have a length of 0.37 seconds and are weighted by a Hanning window with an overlap factor of 31/32. This strategy results in the extraction of one sub-fingerprint for every 11.6 milliseconds. In the worst-case scenario the frame boundaries used during identification are 5.8 milliseconds off with respect to the boundaries used in the database of pre-computed fingerprints. The large overlap assures that even in this worst-case scenario the sub-fingerprints of the audio clip to be identified are still very similar to the sub-fingerprints of the same clip in the database. Due to the large overlap subsequent sub-fingerprints have a large similarity and are slowly varying in time.
The most important perceptual audio features live in the frequency domain. Therefore a spectral representation is computed by performing a Fourier transform on every frame. Due to the sensitivity of the phase of the Fourier transform to different frame boundaries and the fact that the Human Auditory System (HAS) is relatively insensitive to phase, only the absolute value of the spectrum, i.e. the power spectral density, is retained.
In order to extract a 32-bit sub-fingerprint value for every frame, 33 non-overlapping frequency bands are selected. These bands lie in the range from 300 Hz to 2000 Hz (the most relevant spectral range for the HAS) and have a logarithmic spacing. The logarithmic spacing is chosen, because it is known that the HAS operates on approximately logarithmic bands (the so-called Bark scale). Experimentally it was verified that the sign of energy differences (simultaneously along the time and frequency axes) is a property that is very robust to many kinds of processing.
Additional information on deriving fingerprints is provided in the Cano paper, A Review of Audio Fingerprinting, referenced above. Three paragraphs from that reference—discussing linear transforms and similarity measures useful in fingerprinting—follow:
The idea behind linear transforms is the projection of the set of measurements to a new set of features. If the transform is suitably chosen, the redundancy is significantly reduced. There are optimal transforms in the sense of information packing and decorrelation properties, like Karhunen-Loeve (KL) or Singular Value Decomposition (SVD). These transforms, however, are problem dependent and computationally complex. For that reason, lower complexity transforms using fixed basis vectors are common. Most CBID methods therefore use standard transforms from time to frequency domain to facilitate efficient compression, noise removal and subsequent processing. Lourens, (for computational simplicity), and Kurth et al., (to model highly distorted sequences, where the time-frequency analysis exhibits distortions), use power measures. The power can still be seen as a simplified time-frequency distribution, with only one frequency bin.
The most common transformation is the Discrete Fourier Transform (DFT). Some other transforms have been proposed: the Discrete Cosine Transform (DCT), the Haar Transform or the Walsh-Hadamard Transform. Richly et al. did a comparison of the DFT and the Walsh-Hadamard Transform that revealed that the DFT is generally less sensitive to shifting. The Modulated Complex Transform (MCLT) used by Mihcak et al. and also by Burges et al. exhibits approximate shift invariance properties.
So far we have presented an identification framework that follows a template matching paradigm: both the reference patterns—the fingerprints stored in the database—and the test pattern—the fingerprint extracted from the unknown audio—are in the same format and are compared according to some similarity measure, e.g: hamming distance, a correlation and so on. In some systems, only the reference items are actually “fingerprints”—compactly modeled as a codebook or a sequence of indexes to HMMs. In these cases, the similarities are computed directly between the feature sequence extracted from the unknown audio and the reference audio fingerprints stored in the repository. In [E. Allamanche], the feature vector sequence is matched to the different codebooks using a distance metric. For each codebook, the errors are accumulated. The unknown item is assigned to the class which yields the lowest accumulated error. In [E. Bailie], the feature sequence is run against the fingerprints (a concatenation of indexes pointing at HMM sound classes) using the Viterbi algorithm. The most likely passage in the database is selected.
While little has been written about attacks targeting fingerprinting systems, a casual examination of possible attack scenarios reveals several possibilities. A true hacker will probably see many more. Four simple approaches are discussed below.
The reader may be familiar with different loudness profiles selectable on car radios, e.g., Jazz, Talk, Rock, etc. Each applies a different frequency equalization profile to the audio, e.g., making bass notes louder if the Rock setting is selected, and quieter if the Talk setting is selected, etc. The difference is often quite audible when switching between different settings.
However, if the radio is simply turned on and tuned to different stations, the listener is generally unaware of which loudness profile is being employed. That is, without the ability to switch between different profiles, the frequency equalization imposed by a particular loudness profile is typically not noticed by a listener. The different loudness profiles, however, yield different fingerprints.
For example, in the Rock setting, the 300 Hz energy in a particular 0.4 second excerpt may be greater than the 318 Hz energy. However, in the Talk setting, the situation may be reversed. This change prompts a change in the leading bit of the fingerprint.
In practice, an attacker would probably apply loudness profiles more complex than those commonly available in car radios—increasing and decreasing the loudness at many different frequency bands (e.g., 32 different frequency bands). Significantly different fingerprints may thus be produced. Moreover, the loudness profile could change with time—further distancing the resulting fingerprint from the reference values stored in a database.
Another process readily available to attackers is audio multiband compression, a form of processing that is commonly employed by broadcasters to increase the apparent loudness of their signal (most especially commercials). Such tools operate by reducing the dynamic range of a soundtrack—increasing the loudness of quiet passages on a band-by-band basis, to thereby achieve a higher average signal level. Again, this processing of the audio changes its fingerprint, yet is generally not objectionable to the listeners.
The two examples given above are informal attacks—common signal processing techniques that yield, as side-effects, changes in audio fingerprints. Formal attacks—signal processing techniques that are optimized for purposes of changing fingerprints—are numerous.
Some formal attacks are based on psychoacoustic masking. This is the phenomena by which, e.g., a loud sound at one instant (e.g., a drum beat) obscures a listener's ability to perceive a quieter sound at a later instant. Or the phenomena by which a loud sound at one frequency (e.g., 338 Hz) obscures a listener's ability to perceive a quieter sound at a nearby frequency (e.g., 358 Hz) at the same instant. Research in this field goes back decades. (Modern watermarking software employs psychoacoustic masking in an advantageous way, to help hide extra data in audio and video content.)
Hacking software, of course, can likewise examine a song's characteristics and identify the psychoacoustic masking opportunities it presents. Such software can then automatically make slight alterations in the song's frequency components in a way that a listener won't be able to note, yet in a way that will produce a different series of characteristic fingerprints. The processed song will be audibly indistinguishable from the original, but will not “match” any series of fingerprints in the database.
Another formal attack targets fingerprint bit determinations that are near a threshold, and slightly adjusts the signal to swing the outcome the other way. Consider an audio excerpt that has the following respective energy levels (on a scale of 0-99), in the frequency bands indicated:
The algorithm detailed above would generate a fingerprint of {011 . . . } from this data (i.e., 69 is less than 71, so the first bit is ‘0’; 71 is greater than 70, so the second bit is ‘1’; 70 is greater than 68, so the third bit is ‘1’).
Seeing that the energy levels are somewhat close, an attacker tool could slightly adjust the signal's spectral composition, so that the relative energy levels are as follows:
Instead of {011 . . . }, the fingerprint is now {101 . . . }. Two of the three illustrated fingerprint bits have been changed. Yet the change to the audio excerpt is essentially inaudible.
Other fingerprint hacking vulnerabilities arise from shortcuts employed in the database searching strategy—seeking to prune large segments of the data from further searching. For example, the system outlined above confines the large potential search space by assuming that there exists a 32 bit excerpt of the unknown song fingerprint that exactly matches (or matches with only one bit error) a 32 bit excerpt of fingerprint data in the reference database. The system looks at successive 32 bit excerpts from the unknown song fingerprint, and identifies all database fingerprints that include an excerpt presenting a very close match (i.e., 0 or 1 errors). A list of candidate song fingerprints is thereby identified that can be further checked to determine if any meets the looser match criteria generally used. (To allow non-exact fingerprint matches, the system generally allows up to 2047 bit errors in every 8192 bit block of fingerprint data.)
The evident problem is: what if the correct “match” in the database has no 32 bit excerpt that corresponds—with just 1 or 0 bit errors—to a 32 bit excerpt from the unknown song? Such a correct match will never be found—it gets screened out at the outset.
A hacker familiar with the system's principles will see that everything hinges on the assumption that a 32 bit string of fingerprint data will identically match (or match with only one bit error) a corresponding string in the reference database. Since these 32 bits are based on the strengths of 32 narrow frequency bands between 300 Hz and 2000 Hz, the spectrum of the content can readily be tweaked to violate this assumption, forcing a false-negative error. (E.g., notching out two of these narrow bands will force four bits of every 32 to a known state: two will go to zero—since these bands are lower in amplitude than the preceding bands, and two will go to one—since the following bands are higher in amplitude that these preceding, notched, bands). On average, half of these forced bits will be “wrong” (compared to the untweaked music), leading to two bit errors—violating the assumption on which database pruning is based.)
Attacks like the foregoing require a bit of effort. However, once an attacker makes the effort, the resulting hack can be spread quickly and widely.
The exemplary fingerprinting technique noted above (which is understood to be the basis for Gracenote's commercial implementation, MusicID, built from technology licensed from Philips) is not unique in being vulnerable to various attacks. All fingerprinting techniques (including the recently announced MediaHedge, as well as CopySense and RepliCheck) are similarly believed to have vulnerabilities that can be exploited by hackers. (A quandary for potential adopters is that susceptibility of different techniques to different attacks has not been a focus of academic attention.)
It will be recognized that crowdsourcing can help mitigate the vulnerabilities and uncertainties that are inherent in fingerprinting systems. Despite a “no-match” returned from the fingerprint-based content identification system (based on its rote search of the database for a fingerprint that matches that of the altered content), the techniques detailed herein allow human judgment to take a “second look.” Such techniques can identify content that has been altered to avoid its correct identification by fingerprint techniques. (Again, once such identification is made, corresponding information is desirably entered into the database to facilitate identification of the altered content next time.)
It will be recognized that the “crowdsourcing” methodologies detailed above also have applicability to other tasks involved in the arrangements detailed in this specification, including all the documents incorporated by reference.
Implementation of systems according to the present technology is straightforward to artisans, e.g., using standard computer-, database-, software- and network-technology.
Although not particularly illustrated, it will be recognized that the methods described above can be implemented using general purpose (or special purpose) computers, e.g., comprising one or more CPUs, semiconductor memory, hard disks, networking connections, and input-output devices, as are conventional in the art. Software instructions for implementing the above-detailed methods can be stored on tangible media associated with such systems, e.g., disks and semiconductor memories.
To provide a comprehensive disclosure without unduly lengthening this specification, applicants incorporate-by-reference the documents referenced in this disclosure. In addition to those noted elsewhere, these incorporated documents include application Ser. No. 10/979,770 (now U.S. Pat. No. 7,314,162) and Ser. No. 11/132,724 (published as US20050288952); published applications US20030052768, US20030099379. US20030115459, US20030216988, US20040059953, US20040064415, US20040153663, US20040189441, US20040205030, US20040213437, US20040230527, US20040245330, US20050039057, US20050132235, US20050154924, and US20050171851, and issued U.S. Pat. Nos. 5,679,938, 5,679,940, 6,513,018, 6,597,775, 6,944,604, 6,965,889, and 6,968,328.
It is expressly contemplated that the technologies, features and analytical methods detailed herein can be incorporated into the methods/systems detailed in such other documents. Moreover, the technologies, features, and analytical methods detailed in those documents can be incorporated into the methods/systems detailed herein. (It will be recognized that the brief synopses of prior documents provided above naturally do not reflect all of the features found in such disclosures.)
In view of the wide variety of embodiments to which the principles and features discussed above can be applied, it should be apparent that the detailed embodiments are illustrative only and should not be taken as limiting the scope of the disclosed technology. Rather, I claim all such modifications as may come within the scope and spirit of the following claims and equivalents thereof.
This application is a continuation of U.S. patent application Ser. No. 14/519,973, filed Oct. 21, 2014 (now U.S. Pat. No. 9,292,513) which is a continuation of U.S. patent application Ser. No. 13/909,834, filed Jun. 4, 2013 (now U.S. Pat. No. 8,868,917), which is a continuation of U.S. patent application Ser. No. 13/714,930, filed Dec. 14, 2012 (now U.S. Pat. No. 8,458,482) which is a continuation of U.S. patent application Ser. No. 12/114,612, filed May 2, 2008 (now U.S. Pat. No. 8,341,412), which is a division of U.S. patent application Ser. No. 11/613,891, filed Dec. 20, 2006 (published as US 2007-0162761 A1), which claims priority to provisional application 60/753,652, filed Dec. 23, 2005. Each of the above patent documents is hereby incorporated herein by reference in its entirety. Some of the subject matter herein is related to that in various of the assignee's other patent applications, including Ser. No. 10/723,240, filed Nov. 26, 2003 (published as US20040213437); Ser. No. 10/979,770, filed Nov. 1, 2004 (now U.S. Pat. No. 7,314,162); and Ser. No. 11/132,724, filed May 18, 2005 (published as US20050288952).
Number | Name | Date | Kind |
---|---|---|---|
4677466 | Lert et al. | Jun 1987 | A |
5210820 | Kenyon | May 1993 | A |
5629980 | Stefik | May 1997 | A |
5634012 | Stefik et al. | May 1997 | A |
5664018 | Leighton | Sep 1997 | A |
5679938 | Templeton | Oct 1997 | A |
5679940 | Templeton | Oct 1997 | A |
5715403 | Stefik | Feb 1998 | A |
5765152 | Erickson | Jun 1998 | A |
5892536 | Logan et al. | Apr 1999 | A |
5910987 | Ginter | Jun 1999 | A |
5913205 | Jain et al. | Jun 1999 | A |
5918223 | Blum et al. | Jun 1999 | A |
5983351 | Glogau | Nov 1999 | A |
5991429 | Coffin | Nov 1999 | A |
6035055 | Wang et al. | Mar 2000 | A |
6055538 | Kessenich | Apr 2000 | A |
6081788 | Appleman | Jun 2000 | A |
6091822 | Mellows et al. | Jul 2000 | A |
6121530 | Sonoda | Sep 2000 | A |
6122403 | Rhoads | Sep 2000 | A |
6236971 | Stefik | May 2001 | B1 |
6251016 | Tsuda | Jun 2001 | B1 |
6292575 | Bortolussi et al. | Sep 2001 | B1 |
6295439 | Bejar | Sep 2001 | B1 |
6301370 | Steffens et al. | Oct 2001 | B1 |
6401118 | Thomas | Jun 2002 | B1 |
6407680 | Lai et al. | Jun 2002 | B1 |
6430306 | Slocum et al. | Aug 2002 | B2 |
6466695 | Potzsch et al. | Oct 2002 | B1 |
6493744 | Emens | Dec 2002 | B1 |
6505160 | Levy et al. | Jan 2003 | B1 |
6513018 | Culhane | Jan 2003 | B1 |
6546135 | Lin | Apr 2003 | B1 |
6563950 | Wiskott et al. | May 2003 | B1 |
6574609 | Downs | Jun 2003 | B1 |
6597775 | Lawyer et al. | Jul 2003 | B2 |
6603921 | Kanevsky | Aug 2003 | B1 |
6647548 | Lu | Nov 2003 | B1 |
6684254 | Dutta | Jan 2004 | B1 |
6693236 | Gould et al. | Feb 2004 | B1 |
6772196 | Kirsch et al. | Aug 2004 | B1 |
6783459 | Cumbers | Aug 2004 | B2 |
6795638 | Skelley | Sep 2004 | B1 |
6807634 | Braudaway | Oct 2004 | B1 |
6810388 | Sato | Oct 2004 | B1 |
6829368 | Meyer et al. | Dec 2004 | B2 |
6834308 | Ikezoye | Dec 2004 | B1 |
6871200 | MacQueen et al. | Mar 2005 | B2 |
6889383 | Jarman | May 2005 | B1 |
6898799 | Jarman | May 2005 | B1 |
6944604 | Majoor | Sep 2005 | B1 |
6947571 | Rhoads | Sep 2005 | B1 |
6948657 | Sugino | Sep 2005 | B2 |
6952769 | Dubey | Oct 2005 | B1 |
6965889 | Serrano-Morales et al. | Nov 2005 | B2 |
6968328 | Kintzer et al. | Nov 2005 | B1 |
6976165 | Carpentier et al. | Dec 2005 | B1 |
6983371 | Hurtado et al. | Jan 2006 | B1 |
6990453 | Wang | Jan 2006 | B2 |
7003131 | Watson et al. | Feb 2006 | B2 |
7020635 | Hamilton et al. | Mar 2006 | B2 |
7043473 | Rassool et al. | May 2006 | B1 |
7047241 | Erickson | May 2006 | B1 |
7085741 | Lao et al. | Aug 2006 | B2 |
7113615 | Rhoads | Sep 2006 | B2 |
7117513 | Nelson | Oct 2006 | B2 |
7120273 | Robins | Oct 2006 | B2 |
7159116 | Moskowitz | Jan 2007 | B2 |
7185201 | Rhoads | Feb 2007 | B2 |
7194490 | Zee | Mar 2007 | B2 |
7197459 | Harinarayan | Mar 2007 | B1 |
7266704 | Levy | Sep 2007 | B2 |
7277891 | Howard | Oct 2007 | B2 |
7284255 | Apel | Oct 2007 | B1 |
7298864 | Jones | Nov 2007 | B2 |
7302574 | Conwell | Nov 2007 | B2 |
7308413 | Tota | Dec 2007 | B1 |
7314162 | Carr et al. | Jan 2008 | B2 |
7346472 | Moskowitz et al. | Mar 2008 | B1 |
7346605 | Hepworth | Mar 2008 | B1 |
7363278 | Schmelzer | Apr 2008 | B2 |
7366787 | Salas et al. | Apr 2008 | B2 |
7369677 | Petrovic et al. | May 2008 | B2 |
7370017 | Lindeman et al. | May 2008 | B1 |
7379214 | Matsumoto | May 2008 | B2 |
7421723 | Harkness | Sep 2008 | B2 |
7444403 | Packer | Oct 2008 | B1 |
7529659 | Wold | May 2009 | B2 |
7562012 | Wold et al. | Jul 2009 | B1 |
7653552 | Vaidyanathan et al. | Jan 2010 | B2 |
7681032 | Peled et al. | Mar 2010 | B2 |
7689532 | Levy | Mar 2010 | B1 |
7702591 | Nuttall | Apr 2010 | B2 |
7703140 | Nath | Apr 2010 | B2 |
7707427 | Kenrich et al. | Apr 2010 | B1 |
7711731 | Amir et al. | May 2010 | B2 |
7730316 | Baccash | Jun 2010 | B1 |
7757075 | Detreville | Jul 2010 | B2 |
7783489 | Kenyon et al. | Aug 2010 | B2 |
7831531 | Baluja et al. | Nov 2010 | B1 |
7870574 | Kenyon | Jan 2011 | B2 |
7877438 | Schrempp et al. | Jan 2011 | B2 |
7881957 | Cohen et al. | Feb 2011 | B1 |
7899694 | Marshall | Mar 2011 | B1 |
7945470 | Cohen et al. | May 2011 | B1 |
8010511 | Brock et al. | Aug 2011 | B2 |
8090717 | Bharat et al. | Jan 2012 | B1 |
8185967 | Levy | May 2012 | B2 |
8341412 | Conwell | Dec 2012 | B2 |
8458482 | Conwell | Jun 2013 | B2 |
8490206 | Fish | Jul 2013 | B1 |
8688999 | Conwell | Apr 2014 | B2 |
8707459 | Brock et al. | Apr 2014 | B2 |
8738749 | Brock et al. | May 2014 | B2 |
8868917 | Conwell | Oct 2014 | B2 |
9179200 | Davis | Nov 2015 | B2 |
9785841 | Davis | Oct 2017 | B2 |
20010010756 | Ogino | Aug 2001 | A1 |
20010025341 | Marshall | Sep 2001 | A1 |
20020002586 | Rafal | Jan 2002 | A1 |
20020028000 | Conwell | Mar 2002 | A1 |
20020031253 | Dialameh et al. | Mar 2002 | A1 |
20020038296 | Margolus et al. | Mar 2002 | A1 |
20020152215 | Clark et al. | Mar 2002 | A1 |
20020048369 | Ginter et al. | Apr 2002 | A1 |
20020052849 | McCutchen | May 2002 | A1 |
20020052885 | Levy | May 2002 | A1 |
20020069370 | Mack | Jun 2002 | A1 |
20020077986 | Kobata | Jun 2002 | A1 |
20020078441 | Drake | Jun 2002 | A1 |
20020082731 | Pitman et al. | Jun 2002 | A1 |
20020082999 | Lee et al. | Jun 2002 | A1 |
20020083079 | Meier | Jun 2002 | A1 |
20020087885 | Peled et al. | Jul 2002 | A1 |
20020120925 | Logan | Aug 2002 | A1 |
20020132663 | Cumbers | Sep 2002 | A1 |
20020141578 | Ripley | Oct 2002 | A1 |
20020165819 | McKnight et al. | Nov 2002 | A1 |
20020168082 | Razdan | Nov 2002 | A1 |
20020174132 | Silverman | Nov 2002 | A1 |
20020178271 | Graham et al. | Nov 2002 | A1 |
20020178410 | Haitsma et al. | Nov 2002 | A1 |
20030002709 | Wu | Jan 2003 | A1 |
20030018709 | Schrempp | Jan 2003 | A1 |
20030021441 | Levy | Jan 2003 | A1 |
20030033321 | Schrempp | Feb 2003 | A1 |
20030037010 | Schmelzer | Feb 2003 | A1 |
20030052768 | Maune | Mar 2003 | A1 |
20030061490 | Abajian | Mar 2003 | A1 |
20030086341 | Wells | May 2003 | A1 |
20030093790 | Logan et al. | May 2003 | A1 |
20030099379 | Monk et al. | May 2003 | A1 |
20030101104 | Dimitrova et al. | May 2003 | A1 |
20030115459 | Monk | Jun 2003 | A1 |
20030135623 | Schrempp | Jul 2003 | A1 |
20030216988 | Mottett et al. | Nov 2003 | A1 |
20030231785 | Rhoads et al. | Dec 2003 | A1 |
20040009763 | Stone | Jan 2004 | A1 |
20040010417 | Peled | Jan 2004 | A1 |
20040010602 | Van Vleck et al. | Jan 2004 | A1 |
20040019807 | Freund | Jan 2004 | A1 |
20040022444 | Rhoads | Feb 2004 | A1 |
20040044571 | Bronnimann | Mar 2004 | A1 |
20040054661 | Cheung | Mar 2004 | A1 |
20040059953 | Purnell | Mar 2004 | A1 |
20040064415 | Abdallah et al. | Apr 2004 | A1 |
20040071314 | Yacobi | Apr 2004 | A1 |
20040078292 | Blumenau | Apr 2004 | A1 |
20040107166 | Stefik et al. | Jun 2004 | A1 |
20040107348 | Iwamura | Jun 2004 | A1 |
20040133582 | Howard | Jul 2004 | A1 |
20040153663 | Clark et al. | Aug 2004 | A1 |
20040163106 | Schrempp et al. | Aug 2004 | A1 |
20040189441 | Stergiou | Sep 2004 | A1 |
20040205030 | Fox | Oct 2004 | A1 |
20040213437 | Howard | Oct 2004 | A1 |
20040221118 | Slater et al. | Nov 2004 | A1 |
20040225645 | Rowney | Nov 2004 | A1 |
20040230527 | Hansen et al. | Nov 2004 | A1 |
20040230529 | Tieu et al. | Nov 2004 | A1 |
20040236828 | Igeta | Nov 2004 | A1 |
20040243567 | Levy | Dec 2004 | A1 |
20040245330 | Swift et al. | Dec 2004 | A1 |
20040255147 | Peled et al. | Dec 2004 | A1 |
20040267552 | Gilliam et al. | Dec 2004 | A1 |
20050008225 | Yanagisawa et al. | Jan 2005 | A1 |
20050012563 | Kramer | Jan 2005 | A1 |
20050025335 | Bloom et al. | Feb 2005 | A1 |
20050039057 | Bagga et al. | Feb 2005 | A1 |
20050043548 | Cates | Feb 2005 | A1 |
20050043960 | Blankley | Feb 2005 | A1 |
20050049868 | Busayapongchai | Mar 2005 | A1 |
20050063566 | Beek | Mar 2005 | A1 |
20050080846 | McCleskey et al. | Apr 2005 | A1 |
20050102515 | Jaworski et al. | May 2005 | A1 |
20050105726 | Neubauer et al. | May 2005 | A1 |
20050125358 | Levin | Jun 2005 | A1 |
20050132235 | Teunen | Jun 2005 | A1 |
20050141707 | Haitsma | Jun 2005 | A1 |
20050154678 | Schmelzer | Jul 2005 | A1 |
20050154924 | Scheidt et al. | Jul 2005 | A1 |
20050171851 | Applebaum et al. | Aug 2005 | A1 |
20050193016 | Seet et al. | Sep 2005 | A1 |
20050193408 | Sull et al. | Sep 2005 | A1 |
20050213790 | Rhoads | Sep 2005 | A1 |
20050216417 | Risan | Sep 2005 | A1 |
20050222900 | Fuloria et al. | Oct 2005 | A1 |
20050246752 | Liwerant et al. | Nov 2005 | A1 |
20050259819 | Oomen et al. | Nov 2005 | A1 |
20050273612 | Van Der Veen et al. | Dec 2005 | A1 |
20050273617 | Mihcak et al. | Dec 2005 | A1 |
20050276570 | Reed | Dec 2005 | A1 |
20050278787 | Naslund | Dec 2005 | A1 |
20050280502 | Bell | Dec 2005 | A1 |
20050288952 | Davis | Dec 2005 | A1 |
20060029251 | Maeda | Feb 2006 | A1 |
20060031114 | Zommers | Feb 2006 | A1 |
20060031870 | Jarman et al. | Feb 2006 | A1 |
20060034177 | Schrempp | Feb 2006 | A1 |
20060041828 | King | Feb 2006 | A1 |
20060041943 | Singer | Feb 2006 | A1 |
20060050993 | Stentiford | Mar 2006 | A1 |
20060058019 | Chan | Mar 2006 | A1 |
20060059116 | Levi | Mar 2006 | A1 |
20060059561 | Ronning et al. | Mar 2006 | A1 |
20060061599 | Yu | Mar 2006 | A1 |
20060075237 | Seo | Apr 2006 | A1 |
20060080200 | Ashton | Apr 2006 | A1 |
20060080356 | Burges | Apr 2006 | A1 |
20060080703 | Compton | Apr 2006 | A1 |
20060085816 | Funk et al. | Apr 2006 | A1 |
20060086341 | Burges et al. | Apr 2006 | A1 |
20060095586 | Adelman | May 2006 | A1 |
20060101069 | Bell | May 2006 | A1 |
20060106675 | Cohen | May 2006 | A1 |
20060106725 | Finley et al. | May 2006 | A1 |
20060106774 | Cohen | May 2006 | A1 |
20060110137 | Tsuda et al. | May 2006 | A1 |
20060112015 | Chancellor et al. | May 2006 | A1 |
20060115108 | Rodriguez | Jun 2006 | A1 |
20060128470 | Willis | Jun 2006 | A1 |
20060159128 | Chen | Jul 2006 | A1 |
20060171474 | Ramaswamy | Aug 2006 | A1 |
20060174348 | Rhoads | Aug 2006 | A1 |
20060177198 | Jarman et al. | Aug 2006 | A1 |
20060191017 | Hieda | Aug 2006 | A1 |
20060212704 | Kirovski | Sep 2006 | A1 |
20060212927 | Riku et al. | Sep 2006 | A1 |
20060218126 | De Ruijter | Sep 2006 | A1 |
20060218651 | Ginter | Sep 2006 | A1 |
20060230358 | Sacher et al. | Oct 2006 | A1 |
20060240862 | Neven | Oct 2006 | A1 |
20060271512 | Burges | Nov 2006 | A1 |
20060272028 | Maes | Nov 2006 | A1 |
20060277564 | Jarman | Dec 2006 | A1 |
20060287916 | Starr | Dec 2006 | A1 |
20060287996 | Kender et al. | Dec 2006 | A1 |
20070005417 | Desikan | Jan 2007 | A1 |
20070005979 | Ishii | Jan 2007 | A1 |
20070028308 | Nishio et al. | Feb 2007 | A1 |
20070033419 | Kocher | Feb 2007 | A1 |
20070038567 | Allaire et al. | Feb 2007 | A1 |
20070053306 | Stevens | Mar 2007 | A1 |
20070055500 | Bilobrov | Mar 2007 | A1 |
20070058925 | Chiu | Mar 2007 | A1 |
20070061393 | Moore | Mar 2007 | A1 |
20070083883 | Deng | Apr 2007 | A1 |
20070094145 | Ta et al. | Apr 2007 | A1 |
20070098172 | Levy et al. | May 2007 | A1 |
20070101360 | Gutta et al. | May 2007 | A1 |
20070106551 | McGucken | May 2007 | A1 |
20070110010 | Kotola et al. | May 2007 | A1 |
20070118737 | Shimizu | May 2007 | A1 |
20070124756 | Covell et al. | May 2007 | A1 |
20070130015 | Starr et al. | Jun 2007 | A1 |
20070130117 | Lapstun | Jun 2007 | A1 |
20070130126 | Lucosysky | Jun 2007 | A1 |
20070130177 | Schneider | Jun 2007 | A1 |
20070130580 | Covell et al. | Jun 2007 | A1 |
20070156594 | McGucken | Jul 2007 | A1 |
20070157228 | Bayer | Jul 2007 | A1 |
20070157252 | Perez | Jul 2007 | A1 |
20070162349 | Silver | Jul 2007 | A1 |
20070162761 | Davis | Jul 2007 | A1 |
20070168543 | Krikorian et al. | Jul 2007 | A1 |
20070175998 | Lev | Aug 2007 | A1 |
20070180537 | He et al. | Aug 2007 | A1 |
20070192352 | Levy | Aug 2007 | A1 |
20070198426 | Yates | Aug 2007 | A1 |
20070203891 | Solaro | Aug 2007 | A1 |
20070203911 | Chiu | Aug 2007 | A1 |
20070208711 | Rhoads | Sep 2007 | A1 |
20070208715 | Muehlbauer | Sep 2007 | A1 |
20070208751 | Cowan et al. | Sep 2007 | A1 |
20070211174 | Putterman et al. | Sep 2007 | A1 |
20070220575 | Cooper | Sep 2007 | A1 |
20070233556 | Koningstein | Oct 2007 | A1 |
20070234213 | Krikorian et al. | Oct 2007 | A1 |
20070242880 | Stebbings | Oct 2007 | A1 |
20070253594 | Lunt | Nov 2007 | A1 |
20070260520 | Jha | Nov 2007 | A1 |
20070260671 | Harinstein | Nov 2007 | A1 |
20070282472 | Seidman | Dec 2007 | A1 |
20070294173 | Levy et al. | Dec 2007 | A1 |
20080002854 | Tehranchi et al. | Jan 2008 | A1 |
20080004116 | Van | Jan 2008 | A1 |
20080005241 | Cohen | Jan 2008 | A1 |
20080008348 | Metois | Jan 2008 | A1 |
20080010373 | Tojo | Jan 2008 | A1 |
20080027931 | Lu | Jan 2008 | A1 |
20080034396 | Lev | Feb 2008 | A1 |
20080051029 | Witteman | Feb 2008 | A1 |
20080052783 | Levy | Feb 2008 | A1 |
20080059211 | Brock | Mar 2008 | A1 |
20080059285 | Hamoui | Mar 2008 | A1 |
20080059461 | Brock et al. | Mar 2008 | A1 |
20080059536 | Brock | Mar 2008 | A1 |
20080082405 | Martinez et al. | Apr 2008 | A1 |
20080101604 | Kocher | May 2008 | A1 |
20080109306 | Maigret | May 2008 | A1 |
20080109369 | Su | May 2008 | A1 |
20080152146 | Conrado et al. | Jun 2008 | A1 |
20080154401 | Wang | Jun 2008 | A1 |
20080154739 | Kalaboukis | Jun 2008 | A1 |
20080155701 | Martinez et al. | Jun 2008 | A1 |
20080162228 | Mechbach | Jul 2008 | A1 |
20080162449 | Chao-Yu et al. | Jul 2008 | A1 |
20080165960 | Woo | Jul 2008 | A1 |
20080178302 | Brock | Jul 2008 | A1 |
20080209502 | Seidel | Aug 2008 | A1 |
20080235200 | Washington | Sep 2008 | A1 |
20080235795 | Ishikawa | Sep 2008 | A1 |
20080240490 | Finkelstein | Oct 2008 | A1 |
20080249961 | Harkness | Oct 2008 | A1 |
20080275763 | Tran | Nov 2008 | A1 |
20080317278 | Lefebvre et al. | Dec 2008 | A1 |
20090006225 | Multerer | Jan 2009 | A1 |
20090030651 | Wold | Jan 2009 | A1 |
20090052784 | Covell et al. | Feb 2009 | A1 |
20090063279 | Ives | Mar 2009 | A1 |
20090083228 | Shatz et al. | Mar 2009 | A1 |
20090106442 | Liu | Apr 2009 | A1 |
20090119169 | Chandratillake | May 2009 | A1 |
20090129755 | Rakib | May 2009 | A1 |
20090144325 | Chastagnol | Jun 2009 | A1 |
20090144772 | Fink | Jun 2009 | A1 |
20090165031 | Li | Jun 2009 | A1 |
20090313078 | Cross | Dec 2009 | A1 |
20100017487 | Patinkin | Jan 2010 | A1 |
20100119208 | Davis | May 2010 | A1 |
20100191819 | Alspector et al. | Jul 2010 | A1 |
20120011105 | Brock et al. | Jan 2012 | A1 |
20120284803 | Wang et al. | Nov 2012 | A1 |
20130006946 | Prahlad et al. | Jan 2013 | A1 |
20130022333 | Takahashi | Jan 2013 | A1 |
20130085825 | Davis et al. | Apr 2013 | A1 |
20140020116 | Chastagnal et al. | Jan 2014 | A1 |
20150074748 | Brock et al. | Mar 2015 | A1 |
20150302886 | Brock et al. | Oct 2015 | A1 |
Number | Date | Country |
---|---|---|
2010187419 | Aug 2010 | JP |
WO02011033 | Feb 2002 | WO |
WO02065782 | Aug 2002 | WO |
WO02103968 | Dec 2002 | WO |
09042899 | Apr 2009 | WO |
WO09100093 | Aug 2009 | WO |
WO09017049 | Sep 2009 | WO |
Entry |
---|
Allamanche et al. “Content-Based Identification of Audio Material Using Mpeg-7 Low Level Description,” in Proc. of the Int. Symp. of Music Information Retrieval, Indiana, USA, Oct. 2001. |
Amazon Mechanical Turk Developer Guide, 2006, 165 pp., API Version Oct. 31, 2006. |
Amazon Mechanical Turk Developer Guide, Dec. 16, 2005, 94 pp. |
Amazon Mechanical Turk Release Notes, Release Date Oct. 13, 2005 (Oct. 2005). |
Amazon's Mechanical Turk, thread from SlashDot, started Nov. 4, 2005. |
Baluja et al, Content Fingerprinting Using Wavelets, 3rd European Conference on Visual Media Production, Nov. 2006. |
Batlle et al., “Automatic Song Identification in Noisy Broadcast Audio,” in Proc. of the SIP, Aug. 2002 |
Boutin, Crowdsourcing, Consumers as Creators, Business Week, Jul. 13, 2006. |
Brin, et al., “Copy Detection Mechanisms for Digital Documents,” SIGMOD '95, Proceedings of the 1995 ACM SIGMOD international conference on Management of data, pp. 398-409, 1995. |
Cano et al, “A Review of Audio Fingerprinting,” Journal of VLSI Signal Processing, 41, 271, 272, 2005. |
Crowdsourcing article from Wikipedia, Dec. 18, 2006 |
Covell et al, Advertisement Detection and Replacement using Acoustic and Visual Repetition, IEEE Int'l Workshop on Multimedia Signal Processing, Oct. 2006. |
Ghias, et al., “Query By Humming: Musical Information Retrieval in an Audio Database,” ACM Multimedia, pp. 231-236, Nov. 1995. |
Haitsma, et al, “A Highly Robust Audio Fingerprinting System,” Proc. Intl Conf on Music Information Retrieval, 2002. |
Heintze, “Scalable Document Fingerprinting (Extended Abstract),” Bell Laboratories, 1996. |
Howe et al, Crowdsourcing blog at crowdsourcing,typepad.com, Dec. 17, 2006, as retrieved from web.archive.org on Apr. 23, 2008.pdf. |
Howe et al, Crowdsourcing blog at crowsourcing.typepad.com, Nov. 7, 2006, as retrieved from web.archive.org on Apr. 23, 2008.pdf. |
Howe, Look Who's Crowdsourcing, Wired Magazine, Jun. 2006. |
Howe, The Rise of Crowdsourcing, Wired Magazine, Jun. 2006. |
Kageyama et al, “Melody Retrieval with Humming,” Proceedings of Int. Computer Music Conference (ICMC), 1993. |
Kalker et al, “Robust Identification of Audio Using Watermarking and Fingerprinting,” in Multimedia Security Handbook, CRC Press, 2005. |
Konstantinou , et al., “A Dynamic JAVA-Based Intelligent Interface for Online Image Database Searches,” VISUAL'99, LNCS 1614, pp. 211-220, 1999. |
Liu et al, U.S. Appl. No. 60/856,501, filed Nov. 3, 2006, entitled “Rights Management” (which serves as a priority application for published US application 20080109369). |
Manber, “Finding Similar Files in a Large File System,” Jan. 1994 Winter USENIX Technical Conference, 10 pages (as submitted Oct. 1993). |
Release-Amazon Mechanical Turk on Dec. 1, 2006 (Dec. 1, 2006). |
von Ahn, Human Computation, CMU PhD Thesis, Dec. 7, 2005, 87pp. |
Wold et al., “Content-Based Classification, Search and Retrieval of Audio,” IEEE MultiMedia 1996. |
Cheung, et al, Efficient Video Similarity Measurement with Video Signature, IEEE Trans. on Circuits and Systems for Video Technology, 13.1, pp. 59-74, 2003. |
Hoad, et al, Methods for Identifying Versioned and Plagiarized Documents, Journal of the American Society for Information Science and Technology, 54.3, pp. 203-215, 2003. |
Ke, et al, Efficient Near-Duplicate Detection and Sub-Image Retrieval, Intel Research Report IRP-TR-04-03, 2004. |
Popescu, et al, Exposing Digital Forgeries in Color Filter Array Interpolated Images, IEEE Trans. on Signal Processing 53.10, pp. 3948-3959, 2005. |
Brin, et al, Copy detection mechanisms for digital documents, ACM SIGMOD Record, vol. 24, No. 2, 1995. |
DRM Watch, Guba Introduces Video Fingerprint Filtering, Jul. 27, 2006, http://www.drmwatch.com/article.php/3623091. |
Email about the product “Sentinel”, Nov. 14, 2006. |
Global File Registry, Technical White Paper, Draft 1-26, May 2006. |
Krikorian, U.S. Appl. No. 60/823,066, filed Aug. 21, 2006 (priority document for US20070168543). |
Meckbach, U.S. Appl. No. 60/870,817, filed Dec. 19, 2006 (priority document for US20080162228). |
Assignee's U.S. Appl. No. 13/909,834, filed Jun. 4, 2013. |
Jul. 3, 2014 Notice of Appeal, Jan. 3, 2014 final Office Action, and Dec. 3, 2013 Amendment; all from assignee's U.S. Appl. No. 13/686,541 (published as 2013-0085825). |
Jul. 9, 2014 Office Action, and application specification and drawings with a filing date of May 6, 2014; all from assignee's U.S. Appl. No. 14/271,297. |
U.S. Appl. No. 60/823,066, filed Aug. 21, 2006. |
Nov. 21, 2014 Notice of Allowance, Notice of Allowability and Interview Summary; Oct. 29, 2014 Amendment including Interview Summary; Sep. 9, 2014 Interview Summary; Sep. 4, 2014 Amendment including Interview Summary; Jul. 9, 2014 non-final Office Action; all from U.S. Appl. No. 14/271,297. |
Assignee's U.S. Appl. No. 13/937,995, filed Jul. 9, 2013. |
Apr. 27, 2016 Issue Notification; Jan. 20, 2016 Notice of Allowance and Interview Summary; Sep. 11, 2015 Amendment and Terminal Disclaimer; Jun. 11, 2015 Non-final Office Action; all from assignee's U.S. Appl. No. 14/288,124 (published as US 2015-0074748 A1 ). |
May 7, 2014 Issue Notification; Jan. 15, 2014 Notice of Allowance and Interview Summary; Dec. 12, 2013 Amendment; Jun. 14, 2013 Non-final Office Action; Jan. 12, 2012 Amendment submitted with RCE; Oct. 13, 2011 Final Rejection; Aug. 24, 2011 Examiner's Interview Summary; Aug. 15, 2011 Amendment; Apr. 13, 2011 non-final Rejection; Feb. 23, 2011 Amendment submitted with RCE; Dec. 21, 2010 final Rejection; Oct. 1, 2010 Amendment; Jun. 25, 2010 non-final Rejection; Apr. 23, 2010 Examiner's interview summary; Apr. 19, 2010 Amendment; Jan. 13, 2010 non-final Office Action; Dec. 7, 2009 Amendment submitted with RCE; Sep. 3, 2009 final Rejection; Jun. 22, 2009 Amendment; Mar. 17, 2009 non-final Rejection; all from assignee's U.S. Appl. No. 11/512,067 (issued as U.S. Pat. No. 8,738,749). |
Mar. 11, 2016 non-final Office Action; Jan. 14, 2016 Office of Petitions Decision; May 27, 2015 Petition for review by the Office of Petitions; Apr. 22, 2014 claims as filed; all from assignee's U.S. Appl. No. 14/258,633 (published as US 2015-0302886 A1). |
Apr. 2, 2014 Issue Notification; Nov. 25, 2013 Notice of Allowance and Interview Summary; Nov. 5, 2013 Amendment and Interview summary; Jun. 6, 2013 Non-final Office Action; Jun. 11, 2012 Amendment submitted with RCE. |
Feb. 10, 2012 final Rejection; Dec. 19, 2011 Amendment; Sep. 19, 2011 non-final Rejection; Nov. 1, 2010 Amendment submitted with RCE; Jun. 30, 2010 final Rejection; May 17, 2010 Amendment; Jan. 11, 2010 non-final Rejection; all from assignee's U.S. Appl. No. 11/655,748 (issued as U.S. Pat. No. 8,707,459). |
Amazon Mechanical Turk Release Notes, Release Date Oct. 13, 2005. |
BayTSP, Digital Tracking+ Security+ Protection, May 17, 2006 www.baytsp.com/solutions_faq_html. |
BMG Canada Inc., v. Doe, 2005 FCA 193, May 19, 2005. |
BMG Canada Inc., v. Doe, Cross Examination of Gary Millin, Court File No. T-292-04, Feb. 6, 2004. |
Campbell et al. Copy Detection Systems for Digital Documents. IEEE 2000. Retrieved online May 31, 2017. file:///a/Users/jreagan/Documents/e-Red%20Folder/14930298/NPL.pdf. |
Cheung et al., Efficient Video Similarity Measurement and Search, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, 2000. |
Cowboyneal, Slashdot, Microsoft Seeking to Patent Automatic Censorship, May 4, 2006. |
Fetterly et al., Detecting Phrase-Level Duplication on the World Wide Web, Aug. 2005. |
Fetterly et al., On the Evolution of Clusters of Near-Duplicate Web Pages, Oct. 2004. |
U.S. Appl. No. 60/975,158, filed Sep. 25, 2007 (and a priority application for 20080109369). |
Global File Registry, Global File Registry: The economic, scalable, solution for removing infringing content on the Internet, Aug. 23, 2006, www.globalfileregistry.com. |
iCopyright on copyright, Jun. 13, 2006, www.datadepth.com/. |
Indyk et al., Locality-Preserving Hashing in Multidimensional Spaces, 1997. |
Manber, Finding Similar Files in a Large File System, Department of Computer Science, the University of Arizona, Tucson Arizona, Oct. 1993. |
Marc, P2P File Sharing: Altnet Registry is About Money, Not Protection, Aug. 3, 2006, http://www.p2p-webloK.com/50226711/alnet_registry_is_about_money_not_protection.php. |
Nov. 27, 2018 Amendment and Jun. 20, 2017 Office Action, both from assignees U.S. Appl. No. 13/686,541. |
Numly Numbers, Web2.0+ Copyright=Copyright 2.0, Jun. 8, 2006 www.numly.com/numly/default.asp. |
Patent Office file re U.S. Appl. No. 60/870,817 by Meckbach, Method and Device for the Production of Advertising, filed Dec. 19, 2006 (provisional priority case for US20080162228 to Trivid). |
Patent Office file re U.S. Appl. No. 60/891,764 by Weidel, Associating Rights to Multimedia Content, filed Feb. 27, 2007 (provisional priority case for US20080209502 to Motion Picture Laboratories). |
Patent Office file re U.S. Appl. No. 60/910,717 by Harkness, Digital Rights Management and Audience Measurement Systems and Methods, filed Apr. 9, 2007 (provisional priority case for US20080249961 to Nielsen). |
Patent Office file re U.S. Appl. No. 60/914,168 by Harkness, Hardware and Software Architecture to Protect Against Unauthorized Copying of Copyrighted Content, filed Apr. 26, 2007 (provisional priority case for US20080249661 to Nielsen). |
Patent Office file re U.S. Appl. No. 60/919,466 by Harkness, Digital Rights Management and Audience Measurement Systems and Methods, filed Mar. 22, 2007 (provisional priority case for US20080249961). |
Patent Office file re U.S. Appl. No. 60/939,527 by Harkness, Digital Rights Management and Audience Measurement Systems and Methods, filed May 22, 2007 (provisional priority case for US20080249961 to Nielsen). |
Patent Office file re U.S. Appl. No. 60/957,446 by Covell, Fast and Accurate Detection and Classification of Matches Between Time-Based Media, filed Aug. 22, 2007 (provisional priority case for US20090052784 to Google). |
Patent Office file re U.S. Appl. No. 60/968,725 by Ives, Contextual Ads for Video, filed Aug. 29, 2007 (provisional priority case for US20090063279 to TVEyes). |
Patent Office file re U.S. Appl. No. 61/029,155 by Ramaswamy, Method and Apparatus to Control the Transmission of Media Content, filed Feb. 15, 2008 (provisional priority case for US20080249961 to Nielsen). |
Petrovic et al, U.S. Appl. No. 60/833,991, filed Jul. 28, 2006, entitled “Signal Continuity Assessment Using Embedded Watermarks” (which serves as a priority application for US published application for 20080002854). |
Popescu et al., Exposing Digital Forgeries by Detecting Duplicated Image Regions, Department of Computer Science, Dartmouth College, 2005. |
Prosecution excerpts from U.S. Appl. No. 12/048,072, filed Mar. 8, 2008, including applicant submissions dated Mar. 13, 2008, Sep. 14, 2010, Apr. 6, 2011, Jun. 14, 2012, Aug. 7, 2013, Sep. 19, 2013, Apr. 9, 2014, May 12, 2015, and Office papers dated Aug. 10, 2010, Dec. 13, 2010, Mar. 4, 2011, Jun. 24, 2011, Oct. 15, 2013, Feb. 12, 2015, Jul. 10, 2015. |
Prosecution excerpts from U.S. Appl. No. 13/686,541, filed Nov. 27, 2012, including applicant submissions dated Nov. 27, 2012, Apr. 10, 2013, Dec. 3, 2013, and Feb. 3, 2015, and Office documents dated Apr. 9, 2013, Sep. 3, 2013 and Jan. 3, 2014. |
Riya, Visual Search, www.riya.com. |
SNOCAP, Services, Sell Your Music, Aug. 23, 2006 http://www.snocap.com/sell/. |
U.S. Appl. No. 60/753,652, filed Dec. 23, 2005. cited by applicant. |
U.S. Appl. No. 60/856,501, filed Nov. 3, 2006 (and a priority application for US20080109369 to Google). |
U.S. Appl. No. 60/927,940, filed May 3, 2007, which serves as priority application for 20080275763 to Google. |
U.S. Appl. No. 61/026,444, filed Feb. 5, 2008 (and a priority application for WO09100093, and U.S. Appl. No. 12/865,807, to Dolby Laboratories). |
U.S. Appl. No. 15/727,961, filed Oct. 9, 2017. |
U.S. Appl. No. 60/975,158, filed Sep. 25, 2007 (and a priority application for US20080109369 to Google). |
Number | Date | Country | |
---|---|---|---|
20160246878 A1 | Aug 2016 | US |
Number | Date | Country | |
---|---|---|---|
60753652 | Dec 2005 | US |
Number | Date | Country | |
---|---|---|---|
Parent | 11613891 | Dec 2006 | US |
Child | 12114612 | US |
Number | Date | Country | |
---|---|---|---|
Parent | 14519973 | Oct 2014 | US |
Child | 15074967 | US | |
Parent | 13909834 | Jun 2013 | US |
Child | 14519973 | US | |
Parent | 13714930 | Dec 2012 | US |
Child | 13909834 | US | |
Parent | 12114612 | May 2008 | US |
Child | 13714930 | US |