KR20170067517A - Method and apparatus for processing fingerprint - Google Patents

Method and apparatus for processing fingerprint Download PDF

Info

Publication number
KR20170067517A
KR20170067517A KR1020150174260A KR20150174260A KR20170067517A KR 20170067517 A KR20170067517 A KR 20170067517A KR 1020150174260 A KR1020150174260 A KR 1020150174260A KR 20150174260 A KR20150174260 A KR 20150174260A KR 20170067517 A KR20170067517 A KR 20170067517A
Authority
KR
South Korea
Prior art keywords
fingerprint
information
fingerprints
content
metadata
Prior art date
Application number
KR1020150174260A
Other languages
Korean (ko)
Inventor
박태진
백승권
성종모
이태진
최진수
Original Assignee
한국전자통신연구원
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 한국전자통신연구원 filed Critical 한국전자통신연구원
Priority to KR1020150174260A priority Critical patent/KR20170067517A/en
Publication of KR20170067517A publication Critical patent/KR20170067517A/en

Links

Images

Classifications

    • G06F17/30743—
    • G06F17/30778—
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04H—BROADCAST COMMUNICATION
    • H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
    • H04H60/68—Systems specially adapted for using specific information, e.g. geographical or meteorological information
    • H04H60/73—Systems specially adapted for using specific information, e.g. geographical or meteorological information using meta-information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

A fingerprint processing method and a fingerprint processing apparatus are disclosed. The disclosed fingerprint processing method includes extracting fingerprints from an audio signal, determining metadata and broadcast information corresponding to each of the fingerprints, and determining confidence for each fingerprint with each fingerprint and a meta Data and broadcast information, selects a fingerprint having the highest reliability among the fingerprints, and if the reliability of the selected fingerprint is greater than a predetermined reference reliability, extracting the audio signal from the metadata corresponding to the selected fingerprint And determines content information.

Description

METHOD AND APPARATUS FOR PROCESSING FINGERPRINT < RTI ID = 0.0 >

The following description relates to a fingerprint processing method and a fingerprint processing apparatus, and more particularly, to a fingerprint processing method and a fingerprint processing apparatus which include a fingerprint extracted from an audio signal and metadata and broadcast information corresponding to the fingerprint, And more particularly, to a method and system for identifying content.

The audio fingerprinting technique is a technique for correlating a fingerprint, which is a unique characteristic extracted from an audio signal, with audio metadata. In the registration step, the audio fingerprinting technique hash codes the registered fingerprint extracted from the registered audio signal and stores it in the database together with the metadata. In the retrieval step, the metadata corresponding to the registration fingerprint matching the retrieval fingerprint extracted from the audio signal received at the user terminal is output.

The present invention provides a method and an apparatus for improving the accuracy of content information of an audio signal by determining reliability of each fingerprint by applying hypothesis test to metadata and broadcast information corresponding to the fingerprint and the fingerprint .

The present invention preliminarily selects a predetermined number of fingerprints among the fingerprints extracted from the audio signal and preferentially processes the selected fingerprints, thereby reducing the time required for the fingerprint processing, Content information can be provided to the user.

A method of fingerprint processing in accordance with an embodiment includes extracting fingerprints from an audio signal; Determining metadata and broadcast information corresponding to each of the fingerprints; Determining reliability for each of the fingerprints using metadata and broadcast information corresponding to each fingerprint and a corresponding fingerprint; Selecting a fingerprint having the highest reliability among the fingerprints; And determining content information of the audio signal from the metadata corresponding to the selected fingerprint if the reliability of the selected fingerprint is greater than a predetermined reference reliability.

In the fingerprint processing method according to an embodiment, the step of determining reliability for each of the fingerprints may include applying hypothesis testing to each of the fingerprints and metadata corresponding to the fingerprints and the broadcast information Thereby determining the reliability for each of the fingerprints.

The step of determining the content information in the fingerprint processing method according to an exemplary embodiment of the present invention includes the steps of: determining identification information of the content included in the meta data and reproduction information of the content; The content information may be determined to include at least one of the content information.

In the fingerprint processing method according to an exemplary embodiment, the broadcast information may include additional information on the content.

In the fingerprint processing method according to an exemplary embodiment, the broadcast information may include at least one of information on a content broadcast time, information on a content broadcast location, information on a content genre, information on a content broadcast station, information on a content configuration, And information about the information about the user.

In the fingerprint processing method according to an embodiment, the metadata may include at least one of identification information on the content and reproduction information on the content.

A method of fingerprinting according to an embodiment includes comparing the extracted fingerprints and reference fingerprints stored in a database to determine a matching level of each of the extracted fingerprints; And selecting a predetermined number of fingerprints according to a magnitude order of the matching level, wherein the determining metadata and broadcast information comprises: determining metadata and broadcast information corresponding to each of the selected fingerprints, Information can be determined.

In the fingerprint processing method according to an exemplary embodiment, when the reliability of the selected fingerprint is equal to or less than a predetermined reference reliability, the step of selecting the predetermined number of fingerprints includes: A predetermined number of fingerprints can be selected according to the magnitude order of the matching level.

The fingerprint processing method according to an embodiment is characterized in that when the reliability of the selected fingerprint is equal to or smaller than a predetermined reference reliability and there are no fingerprints remaining except for the predetermined fingerprints, And outputting a message indicating that it has failed.

In the fingerprint processing method according to an exemplary embodiment, the fingerprints may include information capable of uniquely identifying contents included in the audio signal.

A fingerprint processing apparatus according to an embodiment includes a receiver for receiving an audio signal; And a processor for extracting and processing fingerprints that can uniquely identify the content included in the audio signal from the audio signal, wherein the processor determines the metadata and broadcast information corresponding to each of the fingerprints Determining reliability for each of the fingerprints by applying hypothesis testing to each fingerprint and metadata and broadcast information corresponding to the fingerprint, and determining reliability of each of the fingerprints, And determines content information of the audio signal from the metadata corresponding to the selected fingerprint if the reliability of the selected fingerprint is greater than a predetermined reference reliability.

In the fingerprint processing apparatus according to an exemplary embodiment, the processor may include at least one of identification information on content included in the metadata, playback information on the content, and external information acquired from an external server using the metadata The content information may be determined.

In the fingerprint processing apparatus according to an exemplary embodiment, the broadcast information may include additional information on the content.

In the fingerprint processing apparatus according to an exemplary embodiment, the broadcast information includes at least one of information on a content broadcast time, information on a content broadcast location, information on a content genre, information on a content broadcast station, information on a content configuration, And information about the information about the user.

In the fingerprint processing apparatus according to an exemplary embodiment, the metadata may include at least one of identification information on the content and reproduction information on the content.

In the fingerprint processing apparatus according to the embodiment, the processor compares the extracted fingerprints and the reference fingerprints stored in the database to determine a matching level of each of the extracted fingerprints, A predetermined number of fingerprints may be selected according to the selected fingerprints, and metadata and broadcast information corresponding to each of the selected fingerprints may be determined.

If the reliability of the selected fingerprint in the fingerprint processing apparatus according to the embodiment is smaller than the predetermined reference reliability, the processor may determine whether the predetermined fingerprint is included in the predetermined fingerprint, The number of fingerprints can be selected.

According to an embodiment of the present invention, the reliability of each fingerprint is determined by applying hypothesis testing to metadata and broadcast information corresponding to the fingerprint and the fingerprint, thereby improving the accuracy of the content information of the audio signal .

According to an embodiment of the present invention, a predetermined number of fingerprints are preferentially selected from the fingerprints extracted from the audio signal, and the preferential processing is performed on the selected fingerprints to obtain the time required for the fingerprint processing And provide content information to the user in a short time.

1 is a diagram illustrating a fingerprint processing apparatus according to an embodiment.
2 is a diagram illustrating a fingerprint processing method according to an embodiment.
FIG. 3 is a diagram for explaining a process of selecting a predetermined number of fingerprints among extracted fingerprints according to an embodiment.
4 is a diagram for explaining the operation of the fingerprint processing apparatus according to whether or not the reliability of the fingerprint selected according to an embodiment is larger than a predetermined reference reliability.
5 is a diagram showing an example of determining content information.
6 is a diagram illustrating a fingerprint processing apparatus according to another embodiment.
7 is a diagram illustrating a fingerprint extracting unit according to an embodiment.

Specific structural or functional descriptions of embodiments are set forth for illustration purposes only and may be embodied with various changes and modifications. Accordingly, the embodiments are not intended to be limited to the particular forms disclosed, and the scope of the disclosure includes changes, equivalents, or alternatives included in the technical idea.

The terms first or second, etc. may be used to describe various elements, but such terms should be interpreted solely for the purpose of distinguishing one element from another. For example, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.

It is to be understood that when an element is referred to as being "connected" to another element, it may be directly connected or connected to the other element, although other elements may be present in between.

The singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, the terms "comprises ", or" having ", and the like, are used to specify one or more of the described features, numbers, steps, operations, elements, But do not preclude the presence or addition of steps, operations, elements, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the meaning of the context in the relevant art and, unless explicitly defined herein, are to be interpreted as ideal or overly formal Do not.

The embodiments described below can be used to identify content contained in an audio signal by processing fingerprints extracted from the audio signal. Embodiments may be implemented in various forms of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent cars, wearable devices, and the like. For example, the embodiments can be applied to identify contents included in an audio signal reproduced in a smart phone, a mobile device, a smart home system, or the like. Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Like reference symbols in the drawings denote like elements.

1 is a diagram illustrating a fingerprint processing apparatus according to an embodiment.

Referring to FIG. 1, a fingerprint processing apparatus 100 includes a receiver 110 and a processor 120. For example, the fingerprint processing device 100 may be implemented as a single processor, or a multiprocessor. Alternatively, the fingerprint processing apparatus 100 may be implemented with a plurality of modules included in different apparatuses. In this case, the plurality of modules may be connected to each other via a network or the like. The fingerprint processing device 100 may be implemented in various computing devices and / or systems such as smart phones, mobile devices, wearable devices, personal computers, laptop computers, tablet computers, intelligent automobiles, televisions, smart home appliances, autonomous vehicles, .

The receiver 110 may receive an audio signal. The receiver 110 receives an audio signal from a microphone built in the fingerprint processing apparatus 100, receives an audio signal stored in the built-in memory, or receives an audio signal stored in an external server through a wired or wireless network by streaming You may.

The processor 120 may extract a fingerprint that can uniquely identify the content included in the audio signal from the audio signal. The processor 120 may determine the content information of the audio signal using the extracted fingerprint.

The fingerprint is used to identify the content included in the audio signal, and may include information that can uniquely identify the content. Unlike a water mark technique that inserts a unique identifier into an audio signal within a range that is not perceived by the human eye or ear, the fingerprint technique allows a unique characteristic inherent in the audio signal So that the contents included in the audio signal can be identified. Information on the identified content can be output as content information.

The processor 120 according to one embodiment determines metadata and broadcast information corresponding to each of the fingerprints. The processor 120 then determines the reliability for each of the fingerprints by applying hypothesis testing to each fingerprint and metadata and broadcast information corresponding to that fingerprint. Then, the processor 120 selects the fingerprint having the highest reliability among the fingerprints. And, if the reliability of the selected fingerprint is greater than the predetermined reference reliability, the processor 120 determines the content information of the audio signal from the metadata corresponding to the selected fingerprint.

2 is a diagram illustrating a fingerprint processing method according to an embodiment.

The fingerprint processing method according to an embodiment may be performed by a processor included in the fingerprint processing apparatus.

In step 210, the fingerprint processing device extracts the fingerprints from the audio signal. The fingerprint processing device may extract a plurality of fingerprints from the audio signal that can uniquely identify the content contained in the audio signal.

The fingerprint processing apparatus can extract a plurality of feature points existing on a spectrogram of an audio signal as a fingerprint. The spectrogram is a two-dimensional visualization of the characteristics of an audio signal. The x-axis of the spectrogram represents time, and the y-axis represents frequency. The fingerprint processing apparatus includes a plurality of feature points present on the spectrogram as (1) frequency information of a reference point corresponding to each feature point, time information, and (2) frequency difference information indicating a relative position difference between reference points corresponding to the feature points And time difference information to determine the fingerprint. For example, when one feature point is located at an upward direction of 50 Hz from the reference point of 0.04 seconds, 0.023 seconds, and the rightward direction of 0.723 seconds, the fingerprint processing apparatus calculates frequency information of the reference point at 400 Hz, time information of 0.042 seconds, , The fingerprint can be determined and extracted based on the rightward direction of the time difference information 0.723 seconds.

In step 220, the fingerprint processing device determines metadata and broadcast information corresponding to each of the fingerprints.

The fingerprint processing device may extract metadata corresponding to each of the fingerprints from the metadata database. The metadata may be indexed information of the fingerprint itself, and may include at least one of identification information on the content and reproduction information on the content. For example, the metadata may include at least one of information on a content title and information on a period in which the content is recently played back.

The metadata may be mapped to a reference fingerprint extracted from the reference audio signal and stored in the metadata database. A plurality of metadata and a plurality of reference fingerprints may be respectively mapped and stored in the metadata database.

The fingerprint processing apparatus compares the extracted fingerprint with a reference fingerprint to determine a reference fingerprint matching the extracted fingerprint, and stores the metadata mapped to the determined reference fingerprint as metadata corresponding to the extracted fingerprint You can decide. If there is no reference fingerprint matching the extracted fingerprint, the fingerprint processor may determine a reference fingerprint that is most similar to the extracted fingerprint, and match the metadata mapped to the determined reference fingerprint to the extracted fingerprint As shown in FIG.

The fingerprint processing device may extract the broadcast information corresponding to each of the fingerprints from the broadcast information database. The broadcast information may include additional information about the content. For example, the broadcast information may include at least one of information on a content broadcast time, information on a content broadcast location, information on a content genre, information on a content broadcast station, information on content configuration, and information on content content rating .

The broadcast information may be mapped to a reference fingerprint extracted from the reference audio signal and stored in the broadcast information database. In the broadcast information database, a plurality of broadcast information and a plurality of reference fingerprints may be mapped and stored, respectively.

The fingerprint processing apparatus compares the extracted fingerprint with a reference fingerprint to determine a reference fingerprint matching the extracted fingerprint, and broadcasts information mapped to the determined reference fingerprint as broadcast information corresponding to the extracted fingerprint You can decide. If there is no reference fingerprint that matches the extracted fingerprint, the fingerprint processor may determine a reference fingerprint that is most similar to the extracted fingerprint, and match the broadcast information mapped to the determined reference fingerprint to the extracted fingerprint It is possible to extract the broadcast information.

The fingerprint processing device may comprise a fingerprint, metadata corresponding to the fingerprint, and broadcast information as a hypothesis set. A more detailed description of the hypothesis set will be described later with reference to FIG.

In step 230, the fingerprinting processor determines reliability for each of the fingerprints using metadata and broadcast information corresponding to each fingerprint and the corresponding fingerprint. The fingerprint processing device may determine reliability for each of the fingerprints by applying hypothesis testing to each fingerprint and metadata and broadcast information corresponding to the fingerprint.

The fingerprints extracted from the received audio signal may include fingerprints from which noise included in the audio signal is extracted. In order to prevent an error in which content information is determined from metadata corresponding to an incorrect fingerprint, the fingerprint processing apparatus considers both the fingerprint and the metadata corresponding to the fingerprint and the broadcast information together to determine the reliability of the fingerprint It is necessary to calculate.

For example, the fingerprint processing apparatus can confirm the broadcast time point of the content from the broadcast information, and can determine the reliability of the fingerprint as the closer the broadcast time point of the confirmed broadcast time point to when the audio signal is received. The user is highly likely to perform a fingerprint search on the content he / she is currently viewing or recently viewed, so that the fingerprint processing apparatus can determine the reliability of the fingerprint in consideration of such matters through the broadcast information.

Also, the fingerprint processing apparatus can confirm the content broadcasting place from the broadcast information, and can determine the reliability of the fingerprint as the closer the location of the confirmed broadcasting station is to the place where the audio signal is received. Since a user residing in Korea is more likely to watch a drama broadcast in Korea than a drama broadcasted in Turkey, the fingerprint processing apparatus can determine the reliability of the fingerprint in consideration of such matters through broadcasting information.

In step 240, the fingerprint processing device selects the fingerprint with the highest reliability among the fingerprints. The fingerprint processing apparatus can select the fingerprint having the highest reliability among the fingerprints whose reliability has been determined.

In step 250, if the reliability of the selected fingerprint is greater than a predetermined reference reliability, the fingerprint processing device determines the content information of the audio signal from the metadata corresponding to the selected fingerprint. The fingerprint processing apparatus can determine the reference reliability in advance by considering the numerical value input from the user or the results that have been processed.

When the reliability of the selected fingerprint is greater than the predetermined reference reliability, the fingerprint processing device can determine that the selected fingerprint is reliable. The fingerprint processing apparatus determines the content information to include at least one of identification information on the content included in the metadata corresponding to the selected fingerprint and external information obtained from the external server using the playback information and metadata of the content .

For example, the fingerprint processing apparatus can determine the content by determining the "drama name" and "episode #" included in the metadata so that the user can identify the content. Alternatively, the fingerprint processing apparatus determines the content information as the "Drama name", "Episode #", and "The last time the user watched" included in the meta data, So that it can be watched subsequently. Alternatively, the fingerprint processing apparatus can determine the content of the "TV program broadcast time" obtained from the external server using the metadata, thereby providing the user with the time for the identified content to be broadcast on the TV.

The operation of the fingerprint processing apparatus when the reliability of the selected fingerprint is lower than the predetermined reference reliability will be described later with reference to FIG.

FIG. 3 is a diagram for explaining a process of selecting a predetermined number of fingerprints among extracted fingerprints according to an embodiment.

In step 310, the fingerprint processing device may compare the fingerprints extracted from the audio signal with the reference fingerprints stored in the database to determine the matching level of each of the extracted fingerprints. At this time, the compared reference fingerprints may be reference fingerprints stored in the metadata database.

For example, when a reference fingerprint matching the extracted fingerprint exists in the metadata database, the fingerprint processing apparatus can determine the matching level of the extracted fingerprint as a maximum value. On the other hand, if there is no reference fingerprint matching the extracted fingerprint, the fingerprint processing device can determine the matching level according to the similarity between the extracted fingerprint and the reference fingerprint most similar to the extracted fingerprint.

In step 320, the fingerprint processing device may select a predetermined number of fingerprints according to the magnitude order of the matching levels. For example, when the predetermined number is 10, the fingerprint processing apparatus can select 10 fingerprints in order of the size of the matching level among the extracted fingerprints.

And, at step 220, the fingerprint processing device may determine metadata and broadcast information corresponding to each of the selected fingerprints.

4 is a diagram for explaining the operation of the fingerprint processing apparatus according to whether or not the reliability of the fingerprint selected according to an embodiment is larger than a predetermined reference reliability.

In step 410, the fingerprint processing device may determine whether the reliability of the selected fingerprint is greater than a predetermined reference reliability.

If the confidence of the selected fingerprint is greater than the predetermined reference confidence, then at step 250, the fingerprint processing device may determine the content information of the audio signal from the metadata corresponding to the selected fingerprint.

Conversely, if the reliability of the selected fingerprint is equal to or lower than the predetermined reference reliability, at step 420, the fingerprint processing device determines whether or not there is a remaining fingerprint except for the fingerprints previously determined at step 320 can do.

If there are remaining fingerprints other than the pre-selected fingerprints, then at step 320, the fingerprint processor may select a predetermined number of fingerprints according to the magnitude order of the matching levels among the remaining fingerprints. Then, at step 220, the fingerprint processing device may determine metadata and broadcast information corresponding to each of the selected fingerprints.

Conversely, if there is no remaining fingerprint except for the predetermined fingerprints, then at step 430, the fingerprint processor outputs a message indicating that the fingerprint search for the audio signal has failed and terminates the operation .

5 is a diagram showing an example of determining content information.

Referring to Figure 5, N hypothesis sets are shown. The fingerprints included in each of the hypothesis sets are extracted from the received audio signal and each hypothesis set may include an incorrect fingerprint due to the noise included in the audio signal. Thus, the fingerprint processing apparatus determines the reliability of the corresponding fingerprint using the fingerprint, the metadata, and the broadcast information included in each hypothesis set, thereby determining the content information from the metadata corresponding to the incorrect fingerprint .

For example, the confidence of fingerprint 1 included in hypothesis set 1 can be determined by applying a hypothesis test to fingerprint 1, metadata 1, and broadcast information 1. Likewise, the reliability of fingerprint 2 included in hypothesis set 2 can be determined by applying hypothesis testing to fingerprint 2, metadata 2, and broadcast information 2. The reliability for the remaining fingerprints can also be determined in the same manner.

If the reliability for the fingerprint 2 is the highest among the fingerprints shown in FIG. 5, the fingerprint processing device determines whether or not the reliability for the fingerprint 2 is higher than a predetermined reference reliability. If the reliability for the fingerprint 2 is higher than the predetermined reference reliability, the fingerprint processing device can determine the content information from the metadata 2.

Conversely, when the reliability for the fingerprint 2 is equal to or lower than the predetermined reference reliability, the fingerprint processing apparatus can newly generate N hypothesis sets by selecting N among the fingerprints except for the predetermined fingerprint have. Then, the fingerprint processing apparatus can repeat the above-described process to determine content information.

6 is a diagram illustrating a fingerprint processing apparatus according to another embodiment.

Referring to FIG. 6, the fingerprint processing apparatus 600 may include a fingerprint extracting unit 610 and a fingerprint matching unit 620.

The fingerprint extractor 610 may extract fingerprints that can uniquely identify the content included in the audio signal from the audio signal. A more detailed operation of the fingerprint extracting unit 610 will be described later with reference to FIG.

The fingerprint matching unit 620 may determine the content information of the audio signal using the extracted fingerprints. The fingerprint matching unit 620 may determine the metadata corresponding to the fingerprints extracted from the metadata database 621 and determine the broadcast information corresponding to the fingerprints extracted from the broadcast information database 622 . The fingerprint matching unit 620 may determine the reliability of each fingerprint using each fingerprint, metadata corresponding to the fingerprint, and broadcast information. The fingerprint matching unit 620 can select the fingerprint having the highest reliability among the fingerprints. If the reliability of the selected fingerprint is greater than the predetermined reference reliability, the fingerprint matching unit 620 may determine the content information of the audio signal from the metadata corresponding to the selected fingerprint.

The operation of the fingerprint processing apparatus 600 shown in FIG. 6 is the same as that of FIG. 1 through FIG. 5, so that detailed description thereof will be omitted.

7 is a diagram illustrating a fingerprint extracting unit according to an embodiment.

7, the fingerprint extracting unit 610 includes a preprocessing unit 710, a framing unit 720, a TF converting unit 730, a feature extracting unit 740, a post-processing unit 750, And a fingerprint modeling unit 760.

The preprocessing unit 710 may improve the accuracy of fingerprint extraction by applying noise elimination or low pass filtering to an audio signal.

The framing unit 720 may divide the preprocessed audio signal into 2 ^ n samples.

The T-F converting unit 730 can change the domain of 2 ^ n samples to the domain of the time-frequency domain using a discrete Fourier transform.

The feature extractor 740 may extract feature points to be used as fingerprints in the time-frequency domain.

The post-processing unit 750 may group the feature points to be used as the fingerprint on the basis of the anchor, and confirm the relative position between the feature point and the reference point.

The fingerprint modeling unit 760 can determine the fingerprint by digitizing the relative position between the minutiae and the reference point. For example, the fingerprint modeling unit 760 may determine the fingerprint using the frequency information of the reference point, the time information, and the frequency difference information and the time difference information indicating the relative positional difference between the minutiae point and the reference point.

The embodiments described above may be implemented in hardware components, software components, and / or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may be implemented within a computer system, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, such as an array, a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For ease of understanding, the processing apparatus may be described as being used singly, but those skilled in the art will recognize that the processing apparatus may have a plurality of processing elements and / As shown in FIG. For example, the processing unit may comprise a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as a parallel processor.

The software may include a computer program, code, instructions, or a combination of one or more of the foregoing, and may be configured to configure the processing device to operate as desired or to process it collectively or collectively Device can be commanded. The software and / or data may be in the form of any type of machine, component, physical device, virtual equipment, computer storage media, or device , Or may be permanently or temporarily embodied in a transmitted signal wave. The software may be distributed over a networked computer system and stored or executed in a distributed manner. The software and data may be stored on one or more computer readable recording media.

The method according to an embodiment may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions to be recorded on the medium may be those specially designed and configured for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Although the embodiments have been described with reference to the drawings, various technical modifications and variations may be applied to those skilled in the art. For example, it is to be understood that the techniques described may be performed in a different order than the described methods, and / or that components of the described systems, structures, devices, circuits, Lt; / RTI > or equivalents, even if it is replaced or replaced.

100: fingerprint processing device
110: receiver
120: Processor

Claims (17)

Extracting fingerprints from the audio signal;
Determining metadata and broadcast information corresponding to each of the fingerprints;
Determining reliability for each of the fingerprints using metadata and broadcast information corresponding to each fingerprint and a corresponding fingerprint;
Selecting a fingerprint having the highest reliability among the fingerprints; And
Determining content information of the audio signal from metadata corresponding to the selected fingerprint if the confidence of the selected fingerprint is greater than a predetermined reference confidence
/ RTI > The method according to claim 1,
Wherein determining confidence for each of the fingerprints comprises:
Wherein confidence for each of the fingerprints is determined by applying hypothesis testing to each fingerprint and metadata and broadcast information corresponding to the fingerprint. The method according to claim 1,
Wherein the step of determining the content information comprises:
Wherein the content information is determined to include at least one of identification information on content included in the metadata, playback information on the content, and external information acquired from an external server using the metadata. The method according to claim 1,
The broadcast information includes:
And additional information about the content. 5. The method of claim 4,
The broadcast information includes:
Wherein the information includes at least one of information on a content broadcast time, information on a content broadcast location, information on a content genre, information on a content broadcast station, information on content configuration, and information on content content rating. The method according to claim 1,
The metadata includes:
The identification information for the content, and the reproduction information for the content. The method according to claim 1,
Comparing the extracted fingerprints and reference fingerprints stored in a database to determine a matching level of each of the extracted fingerprints; And
Selecting a predetermined number of fingerprints according to the magnitude order of the matching level
Further comprising:
Wherein the step of determining the metadata and the broadcast information comprises:
And determining metadata and broadcast information corresponding to each of the selected fingerprints. 8. The method of claim 7,
Wherein if the reliability of the selected fingerprint is equal to or less than a predetermined reference reliability, the step of selecting the predetermined number of fingerprints comprises:
Wherein a predetermined number of fingerprints are selected in accordance with a magnitude order of matching levels among fingerprints other than predetermined fingerprints. 9. The method of claim 8,
Outputting a message indicating that the fingerprint search for the audio signal has failed if the reliability of the selected fingerprint is equal to or smaller than a predetermined reference reliability and there are no fingerprints other than the predetermined fingerprints
Further comprising the steps of: The method according to claim 1,
The fingerprints,
And information that can uniquely identify the content included in the audio signal. A receiver for receiving an audio signal; And
A processor for extracting and processing fingerprints that can uniquely identify the content included in the audio signal from the audio signal,
Lt; / RTI >
The processor comprising:
Determining metadata and broadcast information corresponding to each of the fingerprints,
Determining reliability for each of the fingerprints by applying hypothesis testing to each fingerprint and metadata and broadcast information corresponding to the fingerprint,
Selects a fingerprint having the highest reliability among the fingerprints,
Determining the content information of the audio signal from the metadata corresponding to the selected fingerprint if the reliability of the selected fingerprint is greater than a predetermined reference reliability
A fingerprint processing device. 12. The method of claim 11,
The processor comprising:
And determines the content information to include at least one of identification information on the content included in the meta data, playback information on the content, and external information acquired from an external server using the meta data. 12. The method of claim 11,
The broadcast information includes:
And further information about the content. 14. The method of claim 13,
The broadcast information includes:
Wherein the content information includes at least one of information on a content broadcast time, information on a content broadcast location, information on a content genre, information on a content broadcast station, information on content configuration, and information on content content rating. 12. The method of claim 11,
The metadata includes:
Identification information on the content, and reproduction information on the content. 12. The method of claim 11,
The processor comprising:
Comparing the extracted fingerprints and reference fingerprints stored in a database to determine a matching level of each of the extracted fingerprints,
A predetermined number of fingerprints are selected according to the magnitude order of the matching level,
And determines metadata and broadcast information corresponding to each of the selected fingerprints. 17. The method of claim 16,
If the reliability of the selected fingerprint is less than a predetermined reference reliability,
And selects a predetermined number of fingerprints in accordance with the magnitude order of the matching level among the fingerprints excluding the predetermined fingerprints.
KR1020150174260A 2015-12-08 2015-12-08 Method and apparatus for processing fingerprint KR20170067517A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150174260A KR20170067517A (en) 2015-12-08 2015-12-08 Method and apparatus for processing fingerprint

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150174260A KR20170067517A (en) 2015-12-08 2015-12-08 Method and apparatus for processing fingerprint

Publications (1)

Publication Number Publication Date
KR20170067517A true KR20170067517A (en) 2017-06-16

Family

ID=59278824

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150174260A KR20170067517A (en) 2015-12-08 2015-12-08 Method and apparatus for processing fingerprint

Country Status (1)

Country Link
KR (1) KR20170067517A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020252341A1 (en) * 2019-06-13 2020-12-17 The Nielsen Company (Us), Llc Source classification using hdmi audio metadata

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020252341A1 (en) * 2019-06-13 2020-12-17 The Nielsen Company (Us), Llc Source classification using hdmi audio metadata
US11410680B2 (en) 2019-06-13 2022-08-09 The Nielsen Company (Us), Llc Source classification using HDMI audio metadata
US11907287B2 (en) 2019-06-13 2024-02-20 The Nielsen Company (Us), Llc Source classification using HDMI audio metadata

Similar Documents

Publication Publication Date Title
US20220385963A1 (en) Methods and apparatus to verify and/or correct media lineup information
US20210149939A1 (en) Responding to remote media classification queries using classifier models and context parameters
US10142679B2 (en) Content processing apparatus, content processing method thereof, server information providing method of server and information providing system
CN110083714B (en) Acquisition, recovery, and matching of unique information from file-based media for automatic file detection
US20140245463A1 (en) System and method for accessing multimedia content
US10757468B2 (en) Systems and methods for performing playout of multiple media recordings based on a matching segment among the recordings
CN103077734A (en) Time alignment of recorded audio signals
JP2011505086A (en) System and method for processing digital media
JP2012065052A (en) Information processor and program
US20190306577A1 (en) Signal processing method for determining audience rating of media, and additional information inserting apparatus, media reproducing apparatus and audience rating determining apparatus for performing the same method
KR102233175B1 (en) Method for determining signature actor and for identifying image based on probability of appearance of signature actor and apparatus for the same
US20150310008A1 (en) Clustering and synchronizing multimedia contents
CN110047497B (en) Background audio signal filtering method and device and storage medium
CN113722543A (en) Video similarity comparison method, system and equipment
US20160203824A1 (en) Audio signal communication method and system thereof
KR20180027209A (en) Method and Apparatus for Extracting Audio Fingerprint
CN111246285A (en) Method for separating sound in comment video and method and device for adjusting volume
WO2014117644A1 (en) Matching method and system for audio content
KR20170067517A (en) Method and apparatus for processing fingerprint
WO2017080216A1 (en) Method for recommending video through bluetooth technology, remote controller, and smart tv
CN102314562A (en) Video copyright detecting system and method of audio-video sharing website
WO2017080217A1 (en) Method of recommending video via bluetooth, mobile terminal and in-car video player
US10515624B2 (en) Content processing method and system using audio signal of advertisement data
US9323857B2 (en) System and method for providing content-related information based on digital watermark and fingerprint
KR102160095B1 (en) Method for analysis interval of media contents and service device supporting the same