Abstract: The present disclosure provides a computer-implemented method and system for detecting one or more advertisements broadcasted on a channel in real time. The computer-implemented method includes an extraction of a first set of audio fingerprints and a first set of video fingerprints with a processor. The first set of audio fingerprints and the first set of video fingerprints correspond to a media content broadcasted on the channel. Further, the computer-implemented method includes generation of a set of digital signature values with the processor. The set of digital signature values corresponds to an extracted set of video fingerprints. Furthermore, the computer-implemented method includes detection of the one or more advertisements broadcasted on the channel with the processor.
TECHNICAL FIELD
The present invention relates to the field of digital fingerprinting of media content and, in particular, relates to detection of advertisements using digital audio and video fingerprinting.
5
BACKGROUND
A television broadcast essentially consists of scheduled programs and sponsored advertisements. Each advertisement is generally scheduled to run for 10 to 35 seconds approximately on multiple channels. The advertisements are provided by advertisers to run in between the scheduled broadcast of the program 10 on each channel. These advertisements generate revenues for the company (advertisers) who is into advertising. Also, these advertisements are important source of revenue and marketing for the channels. As the revenue model of each advertiser is closely associated with airing of their own advertisement or their competitor’s advertisements, there is an increased competition between each 15 channel to rope in more advertisers and advertisements. This has created a need for detecting airing, frequency and duration of each advertisement broadcasted on their channel and their competitive channels.
Traditionally, these advertisements are detected through a supervised 20 machine learning based approach and an unsupervised machine learning based approach. The unsupervised machine learning based approach focuses on detection of advertisements by extracting and analyzing digital fingerprints of each advertisement. Similarly, the supervised machine learning based approach focuses on mapping and matching digital fingerprints of each advertisement with 25 a known set of digital fingerprints of corresponding advertisement.
In US patent application US 14/122,674, an advertisement detection system based on fingerprints is provided. The advertisement detection system includes a content stream storage unit storing broadcast content in real time, a 30 section selection unit selecting a reference section and a test section from
Page 3 of 44
broadcast content stored by the storage unit. The advertisement detection system further includes a fingerprint extraction unit extracting fingerprints from the reference section and test section selected by the selection unit and a fingerprint matching unit comparing fingerprints from the test section and reference section. The advertisement detection system extracts the fingerprints and then performing 5 matching between the fingerprints, an advertisement section determination unit determining advertisement segments from the test section based on results of the matching performed by the matching unit, an advertisement DB management unit storing segment information about the advertisement segments determined by the determination unit in an advertisement DB and managing the DB, and a section 10 update unit changing the reference section and test section selected by the selection unit.
In another US patent application US 10/368,235, a system and method for learning-based automatic commercial content detection is described. 15 In one aspect, program data is divided into multiple segments. The segments are analyzed to determine visual, audio, and context-based feature sets that differentiate commercial content from non-commercial content. The context-based features are a function of single-side left and/or right neighborhoods of segments of the multiple segments. 20
In yet another US patent application US 11/397,815, a method and system for detection of video segments in compressed digital video streams is presented. The compressed digital video stream is examine to determine synchronization points, and the compressed video signal is analyzed following 25 detection of the synchronization points to create video fingerprints that are subsequently compared against a library of stored fingerprints.
The present systems and methods have several disadvantages. Most of the methods and system rely on supervised detection of repeated 30 advertisements. These methods and system are either not able to detect
Page 4 of 44
advertisements or imperfectly determine any new advertisements. In addition, these prior arts lack the precision and accuracy to differentiate programs from advertisements. These prior arts lack any approach and technique for unsupervised detection of any new advertisements.
5
In light of the above stated discussion, there is a need for a method and system which overcomes the above stated disadvantages.
SUMMARY
In an aspect, the present disclosure provides a computer-implemented 10 method for detecting one or more advertisements broadcasted on a channel in real time. The computer-implemented method includes an extraction of a first set of audio fingerprints and a first set of video fingerprints with a processor. The first set of audio fingerprints and the first set of video fingerprints correspond to a media content broadcasted on the channel. Further, the computer-implemented 15 method includes generation of a set of digital signature values with the processor. The set of digital signature values corresponds to an extracted set of video fingerprints. Furthermore, the computer-implemented method includes detection of the one or more advertisements broadcasted on the channel with the processor. The first set of video fingerprints and the audio fingerprints is extracted 20 sequentially in the real time.
In an embodiment of the present disclosure, the computer-implemented method further includes storage of a generated set of digital signature values, the first set of audio fingerprints and the first set of video 25 fingerprints in a first database and a second database.
In an embodiment of the present disclosure, the extraction of the first set of video fingerprints is done by sequentially extracting one or more prominent fingerprints. The one or more prominent fingerprints corresponds to one or more 30
Page 5 of 44
prominent frames of a pre-defined number of frames present in the media content for a pre-defined interval of broadcast.
In an embodiment of the present disclosure, the generation of each digital signature value of the set of digital signature values is done by dividing 5 each prominent frame of the one or more prominent frames into a pre-defined number of blocks. Further, each block of each prominent frame of the one or more prominent frames is gray scaled. Furthermore, the generation of each digital signature value of the set of digital signature values is done by calculating a first bit value and a second bit value for each block of the prominent frame. In 10 addition, the generation of each digital signature value of the set of digital signature values is done by obtaining a 32 bit digital signature value corresponding to each prominent frame. Each block of the pre-defined number of block has a pre-defined number of pixels. The first bit value and the second bit value is calculated from comparison of a mean and a variance for the pre-defined 15 number of pixels in each block of the prominent frame with a corresponding mean and variance for a master frame. The corresponding mean and variance for the master frame is present in the master database. The 32 bit digital signature value is obtained by sequentially arranging the first bit value and the second bit value for each block of the pre-defined number of blocks of the prominent frame. 20
In an embodiment of the present disclosure, the first bit value and the second bit value are assigned a binary 0 when the mean and the variance for each block of the prominent frame is less the corresponding mean and variance of each master frame. 25
In another embodiment of the present disclosure, the first bit value and the second bit value are assigned a binary 1 when the mean and the variance for each block of the prominent frame is greater than the corresponding mean and variance of each master frame. 30
Page 6 of 44
In an embodiment of the present disclosure, the detection of the one or more advertisements is a supervised detection and an unsupervised detection.
In an embodiment of the present disclosure, the unsupervised detection of the one or more advertisements is done through one or more steps. 5 The one or more steps includes a step of probabilistically matching a first pre-defined number of digital signature values of a real time broadcasted media content with a stored set of digital signature values present in the first database and the second database. The first pre-defined number of digital signature values corresponds to a pre-defined number of prominent frames. Further, the one or 10 more steps include a step of a comparison of one or more prominent frequencies and one or more prominent amplitudes of an extracted first set of audio fingerprints. The one or more steps further include a step of determination of a positive probabilistic match of the pre-defined number of prominent frames based on a pre-defined condition. Furthermore, the one or more steps include a step of 15 fetching of a video and an audio clip corresponding to a probabilistically matched digital signature values. The one or more steps further include a step of checking for presence of the audio and the video clip manually in the master database. In addition, the one or more steps includes a step of reporting a positively matched digital signature values corresponding to an advertisement of the one or more 20 advertisement in a reporting database present in the first database. The probabilistic match is performed for the set of digital signature values by utilizing a temporal recurrence algorithm.
In an embodiment of the present disclosure, the pre-defined condition 25 includes a pre-defined range of positive matches corresponding to probabilistically matched digital signature values, a pre-defined duration of media content corresponding to the positive match. In addition, the predefined condition includes a sequence and an order of the positive matches and a degree of positive match of a pre-defined range of number of bits of the first pre-defined number of 30 signature values.
Page 7 of 44
In an embodiment of the present disclosure, the first pre-defined number of digital signature values of the set of digital signature values for the unsupervised detection of the one or more advertisements is 20.
In an embodiment of the present disclosure, the computer-5 implemented method further includes update of a first metadata comprising the set of digital signature values and the first set of video fingerprints with the processor. The set of digital signature values and the first set of video fingerprints correspond to a detected advertisement and updated manually in the master database for the unsupervised detection. 10
In an embodiment of the present disclosure, the supervised detection of the one or more advertisements is done through one or more steps. The one or more steps includes a step of probabilistically matching a second pre-defined number of digital signature values corresponding to a pre-defined number of 15 prominent frames of a real time broadcasted media content with a stored set of digital signature values. The stored set of digital signature values is present in the master database. Further, the one or more steps includes a step of comparing the one or more prominent frequencies and the one or more prominent amplitudes corresponding to the extracted first set of audio fingerprints with a stored one or 20 more prominent frequencies and a stored one or more prominent amplitudes. Furthermore, the one or more steps include a determination of the positive match in the probabilistically matching of the second pre-defined number of digital signature values with the stored set of digital signature values in the master database. In addition, the one or more steps includes a step of comparing the one 25 or more prominent frequencies and the one or more prominent amplitudes corresponding to the extracted first set of audio fingerprints with the stored one or more prominent frequencies and the stored one or more prominent amplitudes. The probabilistic match being performed for the set of digital signature values by utilizing a sliding window algorithm. 30
Page 8 of 44
In an embodiment of the present disclosure, the second pre-defined number of digital signature values of the set of digital signature values for the supervised detection of the one or more advertisements is 6.
In another aspect, the present disclosure provides a computer 5 program product. The computer program product includes a non-transitory computer readable medium storing a computer readable program. The computer readable program when executed on a computer causes the computer to perform one or more steps. The one or more steps include a step of extracting a first set of audio fingerprints and a first set of video fingerprints corresponding to media 10 content broadcasted on the channel. The one or more steps include a step of generating a set of digital signature values corresponding to an extracted set of video fingerprints. Further, the one or more steps include a step of detecting the one or more advertisements broadcasted on the channel. The first set of video fingerprints and the audio fingerprints is extracted sequentially in the real time. 15
In an embodiment of the present disclosure, the detection of the one or more advertisements is a supervised detection and an unsupervised detection.
In an embodiment of the present disclosure, the unsupervised 20 detection of the one or more advertisements is done through one or more steps. The one or more steps includes a step of probabilistically matching a first pre-defined number of digital signature values of a real time broadcasted media content with a stored set of digital signature values present in the first database and the second database. The first pre-defined number of digital signature values 25 corresponds to a pre-defined number of prominent frames. Further, the one or more steps include a step of a comparison of one or more prominent frequencies and one or more prominent amplitudes of an extracted first set of audio fingerprints. The one or more steps further include a step of determination of a positive probabilistic match of the pre-defined number of prominent frames based 30 on a pre-defined condition. Furthermore, the one or more steps include a step of fetching of a video and an audio clip corresponding to a probabilistically matched
Page 9 of 44
digital signature values. The one or more steps further include a step of checking for presence of the audio and the video clip manually in the master database. In addition, the one or more steps includes a step of reporting a positively matched digital signature values corresponding to an advertisement of the one or more advertisement in a reporting database present in the first database. The 5 probabilistic match is performed for the set of digital signature values by utilizing a temporal recurrence algorithm.
In an embodiment of the present disclosure, the supervised detection of the one or more advertisements is done through one or more steps. The one or 10 more steps includes a step of probabilistically matching a second pre-defined number of digital signature values corresponding to a pre-defined number of prominent frames of a real time broadcasted media content with a stored set of digital signature values. The stored set of digital signature values is present in the master database. Further, the one or more steps includes a step of comparing the 15 one or more prominent frequencies and the one or more prominent amplitudes corresponding to the extracted first set of audio fingerprints with a stored one or more prominent frequencies and a stored one or more prominent amplitudes. Furthermore, the one or more steps include a determination of the positive match in the probabilistically matching of the second pre-defined number of digital 20 signature values with the stored set of digital signature values in the master database. In addition, the one or more steps includes a step of comparing the one or more prominent frequencies and the one or more prominent amplitudes corresponding to the extracted first set of audio fingerprints with the stored one or more prominent frequencies and the stored one or more prominent amplitudes. 25 The probabilistic match being performed for the set of digital signature values by utilizing a sliding window algorithm.
In yet another aspect, the present disclosure provides an advertisement detection system for detecting the one or more advertisements 30 broadcasted on a channel in real time. The advertisement detection system
Page 10 of 44
includes an extraction module in a processor. The extraction module extracts a first set of audio fingerprints and a first set of video fingerprints corresponding to media content broadcasted on the channel. Further, the advertisement detection system includes a generation module in the processor. The generation module generates a set of digital signature values corresponding to an extracted set of 5 video fingerprints. Furthermore, the advertisement detection system includes a detection module in the processor. The detection module detects the one or more advertisements broadcasted on the channel. The first set of video fingerprints and the audio fingerprints is extracted sequentially in the real time.
10
In an embodiment of the present disclosure, the advertisement detection system further includes a storage module in the processor. The storage module stores the generated set of digital signature values, the first set of audio fingerprints and the first set of video fingerprints in a first database and a second database. 15
In an embodiment of the present disclosure, the generation module generates each digital signature value of the set of digital signature values by dividing each prominent frame of the one or more prominent frames into a pre-defined number of blocks. Further, each block of each prominent frame of the 20 one or more prominent frames is gray scaled. Furthermore, the generation of each digital signature value of the set of digital signature values is done by calculating a first bit value and a second bit value for each block of the prominent frame. In addition, the generation of each digital signature value of the set of digital signature values is done by obtaining a 32 bit digital signature value 25 corresponding to each prominent frame. Each block of the pre-defined number of block has a pre-defined number of pixels. The first bit value and the second bit value is calculated from comparison of a mean and a variance for the pre-defined number of pixels in each block of the prominent frame with a corresponding mean and variance for a master frame. The corresponding mean and variance for the 30 master frame is present in the master database. The 32 bit digital signature value
Page 11 of 44
is obtained by sequentially arranging the first bit value and the second bit value for each block of the pre-defined number of blocks of the prominent frame.
This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This 5 Summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
BRIEF DESCRIPTION OF THE FIGURES 10
Having thus described the invention in general terms, reference will now be made to the accompanying drawings, which are not necessarily drawn to scale, and wherein:
FIG. 1A illustrates a system for a supervised and a unsupervised detection of one or more advertisements broadcasted on a channel, in accordance 15 with an embodiment of the present disclosure;
FIG. 1B illustrates a system for the unsupervised detection of the one or more advertisements broadcasted on the channel, in accordance with another embodiment of the present disclosure;
FIG. 1C illustrates a system for the supervised detection of the one or 20 more advertisements broadcasted on the channel, in accordance with yet another embodiment of the present disclosure;
FIG. 2 illustrates a block diagram of an advertisement detection system, in accordance with various embodiments of the present disclosure;
FIG. 3 illustrates a flow chart for the unsupervised detection of the 25 one or more advertisements broadcasted on the channel, in accordance with various embodiments of the present disclosure; and
FIG. 4 illustrates a block diagram of the portable communication device, in accordance with various embodiments of the present disclosure.
Page 12 of 44
It should be noted that the accompanying figures are intended to present illustrations of exemplary embodiments of the present disclosure. These figures are not intended to limit the scope of the present disclosure. It should also be noted that accompanying figures are not necessarily drawn to scale.
5
Page 13 of 44
DETAILED DESCRIPTION
Reference will now be made in detail to selected embodiments of the present disclosure in conjunction with accompanying figures. The embodiments described herein are not intended to limit the scope of the disclosure, and the present disclosure should not be construed as limited to the embodiments 5 described. This disclosure may be embodied in different forms without departing from the scope and spirit of the disclosure. It should be understood that the accompanying figures are intended and provided to illustrate embodiments of the disclosure described below and are not necessarily drawn to scale. In the drawings, like numbers refer to like elements throughout, and thicknesses and 10 dimensions of some components may be exaggerated for providing better clarity and ease of understanding.
It should be noted that the terms "first", "second", and the like, herein do not denote any order, quantity, or importance, but rather are used to distinguish 15 one element from another. Further, the terms "a" and "an" herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced item.
FIG. 1A illustrates a system 100 for a supervised and an unsupervised 20 detection of one or more advertisements broadcasted on a channel, in accordance with an embodiment of the present disclosure. The system 100 describes an environment suitable for an interactive reception and processing of a channel broadcast. The system 100 is configured to provide a setup for detection of the one or more advertisements. 25
The system 100 includes a broadcast reception device 102, an advertisement detection system 104 and a master database 112. The above stated elements of the system 100 operate coherently and synchronously to detect the one or more advertisements present in media content broadcasted in the channel. 30 The broadcast reception device 102 is a channel feed receiving and processing
Page 14 of 44
device. The broadcast reception device 102 is attached directly or indirectly to a receiving antenna or dish. The receiving antenna receives a broadcasted signal carrying one or more channel feeds. The one or more channel feeds are encoded in a pre-defined format. In addition, the one or more channel feeds have a set of characteristics. The set of characteristics includes a frame rate, an audio sample 5 rate, one or more frequencies and the like.
The broadcasted signal carrying the one or more channel feeds is initially transmitted from a transmission device. In an embodiment of the present disclosure, the broadcasted signal carrying the one or more channel feeds is a 10 multiplexed MPEG-2 encoded signal having a constant bit rate. In another embodiment of the present disclosure, the broadcasted signal carrying the one or more channel feeds is a multiplexed MPEG-2 encoded signal having a variable bit rate. In yet another embodiment of the present disclosure, the broadcasted signal carrying the one or more channel feeds is any digital standard encoded signal. 15 The bit rate is based on complexity of each frame in each of the one or more channel feeds. The quality of the multiplexed MPEG-2 encoded signal will be reduced when the broadcasted signal is too complex to be coded at a constant bit-rate. The bit rate of the variable bit-rate MPEG-2 streams is adjusted dynamically as less bandwidth is needed to encode the images with a given picture quality. In 20 addition, the broadcasted signal is encrypted for a conditional access to a particular subscriber. The encrypted broadcast signal is uniquely decoded by the broadcast reception device 102 uniquely.
In an example, a digital TV signal is received on the broadcast 25 reception device 102 as a stream of MPEG-2 data. The MPEG-2 data has a transport stream. The transport stream has a data rate of 40 megabits/second for a cable or satellite network. Each transport stream consists of a set of sub-streams. The set of sub-streams is defined as elementary streams. Each elementary stream includes an MPEG-2 encoded audio, an MPEG-2 encoded video and data 30 encapsulated in an MPEG-2 stream. In addition, each elementary stream includes
Page 15 of 44
a packet identifier (hereinafter “PID”) that acts as a unique identifier for corresponding elementary stream within the transport stream. The elementary streams are split into packets in order to obtain a packetized elementary stream (hereinafter “PES”).
5
In an embodiment of the present disclosure, the broadcast reception device 102 is a digital set top box. In another embodiment of the present disclosure, the broadcast reception device 102 is a hybrid set top box. In yet another embodiment of the present disclosure, the broadcast reception device 102 is any standard broadcast signal processing device. Further, the broadcast 10 reception device 102 may receive the broadcast signal from any broadcast signal medium. In an embodiment of the present disclosure, the broadcast signal medium is an ethernet cable. In another embodiment of the present disclosure, the broadcast signal medium is a satellite dish. In yet another embodiment of the present disclosure, the broadcast signal medium is a coaxial cable. In yet another 15 embodiment of the present disclosure, the broadcast signal medium is a telephone line having DSL connection. In yet another embodiment of the present disclosure, the broadcast signal medium is a broadband over power line (hereinafter “BPL”). In yet another embodiment of the present disclosure, the broadcast signal medium is an ordinary VHF or UHF antenna. 20
The broadcast reception device 102 primarily includes a signal input port, an audio output port, a video output port, a de-multiplexer, a video decoder, an audio decoder and a graphics engine. The broadcast signal carrying the one or more channel feeds is received at the signal input port. The broadcast signal 25 carrying the one or more channel feeds is de-multiplexed by the de-multiplexer. The video decoder decodes the encoded video and the audio decoder decodes the encoded audio. The video and audio corresponds to a channel selected in the broadcast reception device 102. In general, the broadcast reception device 102 carries the one or more channel feeds multiplexed to form a single transporting 30
Page 16 of 44
stream. The broadcast reception device 102 can decode only one channel in real time.
Further, the decoded audio and the decoded video are received at the audio output port and the video output port. Further, the decoded video has a first 5 set of features. The first set of features includes a frame height, a frame width, a frame rate, a video resolution, a bit rate and the like. Moreover, the decoded audio has a second set of features. The second set of features includes a sample rate, a bit rate, a bin size, one or more data points, one or more prominent frequencies and one or more prominent amplitudes. Further, the decoded video 10 may be of any standard quality. In an embodiment of the present disclosure, the decoded video signal is a 144p signal. In another embodiment of the present disclosure, the decoded video signal is a 240p signal. In yet another embodiment of the present disclosure, the decoded video signal is a 360p signal. In yet another embodiment of the present disclosure, the decoded video signal is a 480p signal. 15 In yet another embodiment of the present disclosure, the decoded video signal is a 720p video signal. In yet another embodiment of the present disclosure, the decoded video signal is a 1080p video signal. In yet another embodiment of the present disclosure, the decoded video signal is a 1080i video signal. Here, p and i denotes progressive scan and interlace scan techniques. 20
Further, the decoded video and the decoded audio (hereinafter “media content”) are transferred to the advertisement detection system 104 through a transfer medium. The transfer medium can be a wireless medium or a wired medium. Moreover, the media content includes one or more television programs, 25 the one or more advertisements, one or more channel related data, subscription related data, operator messages and the like. The media content has a pre-defined frame rate, a pre-defined number of frames and a pre-defined bit rate for a pre-defined interval of broadcast. The advertisement detection system 104 includes a first processing unit 106 and a second processing unit 108. The advertisement 30 detection system 104 has a built in media splitter configured to copy and transmit
Page 17 of 44
the media content synchronously to the first processing unit 106 and the second processing unit 108 in the real time. The first processing unit 106 includes a first central processing unit and associated peripherals for unsupervised detection of the one or more advertisements (also shown in FIG. 1B). The first processing unit 106 is connected to a first database 106a. 5
In an embodiment of the present disclosure, the first processing unit 106 performs histogram normalization of each frame of the media content broadcasted on the channel. The first processing unit 106 performs the histogram normalization. The first processing unit 106 sets each pixel value in each frame 10 of the media content to a standard pixel value range set as a standard for each detected advertisement. In another embodiment of the present disclosure, the first processing unit 106 skips the histogram normalization.
In an embodiment of the present disclosure, the first processing unit 15 106 scales each frame of the media content to a pre-defined scale. In an embodiment of the present disclosure, the pre-defined scale of each frame is 640 by 480. In an embodiment of the present disclosure, the scaling of each frame is done by trimming a first region corresponding to a channel logo and a second region corresponding to a channel’s dynamic ticker. In another embodiment of 20 the present disclosure, the scaling of each frame is done by trimming the first region corresponding to the channel’s dynamic ticker and the second region corresponding to the channel logo. In another embodiment of the present disclosure, the first processing unit 106 skips the scaling of each frame when each frame has the pre-defined scale. 25
The first processing unit 106 performs extraction of a first set of audio fingerprints and a first set of video fingerprints corresponding to the media content broadcasted on the channel. The first set of video fingerprints and the first set of audio fingerprints are extracted sequentially in the real time. The 30 extraction of the first set of video fingerprints is done by sequentially extracting
Page 18 of 44
one or more prominent fingerprints corresponding to one or more prominent frames present in the media content. The one or more prominent frames correspond to the pre-defined interval of broadcast.
For example, let the media content be related to a channel say, X. 5 The channel X broadcasts a 1 hour drama show between 10 AM to 11 AM. Suppose the media content is broadcasted on the channel X with a frame rate of 25 frames per second (hereinafter “fps”). Again let us assume that the channel X administrator has placed 5 advertisements in between 1 hour broadcast of the drama show. The first processing unit 106 separates audio and video from the 10 media content corresponding to the drama show in the real time. Further, the first processing unit 106 sets a pre-defined range of time to approximate duration of play of every advertisement. Let us suppose the pre-defined range of time is between 10 seconds to 35 seconds. The first processing unit 106 processes each frame of the pre-defined number of frames of the 1 hour long drama show. The 15 first processing unit 106 filters and selects prominent frames having dissimilar scenes. The first processing unit 106 extracts relevant characteristics corresponding to each prominent frame. The relevant characteristics constitute a digital video fingerprint. Similarly, the first processing unit 106 extracts the first set of audio fingerprints corresponding to the media content. 20
Furthermore, each of the one or more prominent fingerprints corresponds to a prominent frame having sufficient contrasting features compared to an adjacent prominent frame. For example, let us suppose that the first processing unit 106 select 5 prominent frames per second from 25 frames per 25 second. Each pair of adjacent frames of the 5 prominent frames will have evident contrasting features. The first processing unit 106 generates a set of digital signature values corresponding to an extracted set of video fingerprints. The first processing unit 106 generates each digital signature value of the set of digital signature values by dividing each prominent frame of the one or more prominent 30 frames into a pre-defined number of blocks. In an embodiment of the present
Page 19 of 44
disclosure, the predefined number of block is 15 (4X4). In another embodiment of the present disclosure, the pre-defined number of blocks is any suitable number. Each block of the pre-defined number of blocks has a pre-defined number of pixels. Each pixel is fundamentally a combination of red (hereinafter “R”), green (hereinafter “G”) and blue (hereinafter “B”) colors. The colors are 5 collectively referred to as RGB. Each color of a pixel (RGB) has a pre-defined value in a pre-defined range of values. The predefined range of values is 0-255.
In an example, the RGB for the pixel has value of 000000. The color of pixel is black. In another example, the RGB for the pixel has a value of 10 FFFFFF (255; 255; 255). The color of the pixel is white. Here, FF is hexadecimal equivalent of decimal, 255. In yet another example, the RGB for the pixel has a value of CCCC00 (204; 204; 0). The color of the pixel is yellow. The first processing unit 106 gray-scales each block of each prominent frame of the one or more prominent frames. The gray-scaling of each block is a conversion of 15 RGB to monochromatic shades of grey color. Here 0 represents black and 255 represents white. Further, the first processing unit 106 calculates a first bit value and a second bit value for each block of the prominent frame. The first bit value and the second bit value are calculated from comparing a mean and a variance for the pre-defined number of pixels in each block of the prominent frame with a 20 corresponding mean and variance for a master frame in the master database 112. The first processing unit 106 assigns the first bit value and the second bit with a binary 0 when the mean and the variance for each block of the prominent frame is less the corresponding mean and variance of each master frame. The first processing unit 106 assigns the first bit value and the second bit value with a 25 binary 1 when the mean and the variance for each block is greater than the corresponding mean and variance of each master frame.
Furthermore, the first processing unit 106 obtains a 32 bit digital signature value corresponding to each prominent frame. The 32 bit digital 30 signature value is obtained by sequentially arranging the first bit value and the
Page 20 of 44
second bit value for each block of the pre-defined number of blocks of the prominent frame. The first processing unit 106 stores each digital signature value corresponding to each prominent frame of the one or more prominent frames in the first database 106a. The digital signature value corresponds to the one or more programs and the one or more advertisements. The first processing unit 106 5 utilizes a temporal recurrence algorithm to detect the one or more advertisements. In temporal recurrence algorithm, the first processing unit 106 probabilistically matches a first pre-defined number of digital signature values with a stored set of digital signature values present in the first database 106a.
10
In an example, let us suppose that the first processing unit 106 generates 100 digital signature values corresponding to 100 prominent frames in the first database 106a. The first processing unit 106 probabilistically matches 20 digital signature values corresponding to 101st to 121st prominent frame with each 20 digital signature values corresponding to 100 previously stored prominent 15 frames.
The probabilistic match of the first pre-defined number of digital signature values sequentially for each of the prominent frame is performed by utilizing a sliding window algorithm. In an embodiment of the present disclosure, 20 the first pre-defined number of digital signature values of the set of digital signature values for the unsupervised detection of the one or more advertisements is 20. The first processing unit 106 determines a positive probabilistic match of the pre-defined number of prominent frames based on a pre-defined condition. The pre-defined condition includes a pre-defined range of positive matches 25 corresponding to probabilistically match digital signature values and a pre-defined duration of media content corresponding to the positive match. In addition, the pre-defined condition includes a sequence and an order of the positive matches and a degree of match of a pre-defined range of number of bits of the first pre-defined number of signature values. In an embodiment of the present disclosure, 30 the pre-defined range of probabilistic matches corresponding to the positive match
Page 21 of 44
lies in a range of 40 matches to 300 matches. In another embodiment of the present disclosure, the pre-defined range of range of probabilistic matches corresponding to the positive match lies in a suitable duration of each advertisement running time. In an embodiment of the present disclosure, the first processing unit 106 discards the probabilistic matches corresponding to less than 5 40 positive matches.
Further, the pre-defined duration of media content corresponding to the positive match has a first limiting duration bounded by a second limiting duration. In an embodiment of the present disclosure, the first limiting duration is 10 10 seconds and the second limiting duration is 25 seconds. In another embodiment of the present disclosure, the first limiting duration is 10 seconds and the second limiting duration is 35 seconds. In yet another embodiment of the present disclosure, the first limiting duration is 10 seconds and the second limiting duration is 60 seconds. In yet another embodiment of the present disclosure, the 15 first limiting duration is 10 seconds and the second limiting duration is 90 seconds. In yet another embodiment of the present disclosure, the first limiting duration and the second limiting duration may have any suitable limiting durations.
20
In an example, suppose 100 digital signature values from 1000th prominent frame to 1100th prominent frame gives a positive match with a stored 100th frame to 200th frame in the first database 106a. The first processing unit 106 checks whether the number of positive matches in the pre-defined range of positive matches and the positive matches correspond to media content in the first 25 limiting duration and the second limiting duration. In addition, the first processing unit 106 checks whether the positive matches of 100 digital signature values for unsupervised detection of the one or more advertisements is in a required sequence and order.
30
Page 22 of 44
The first processing unit 106 checks for the degree of match of the pre-defined range of number of bits of the first pre-defined number of signature values. In an example, the degree of match of 640 bits (32 Bits X 20 digital signature values) of the generated set of digital signature values with stored 640 digital signature values is 620 bits. In such case, the first processing unit 106 5 flags the probabilistic match as the positive match. In another example, the degree of match of 640 bits of the generated set of digital signature values with stored 640 digital signature values is 550 bits. In such case, the first processing unit 106 flags the probabilistic match as the negative match. In an embodiment of the present disclosure, the pre-defined range of number of bits is 0-40. 10
The first processing unit 106 generates one or more prominent frequencies and one or more prominent amplitudes from extracted first set of audio fingerprints. The first processing unit 106 fetches a sample rate of first set of audio fingerprints. The sample rate is divided by a pre-defined bin size set for 15 the audio. The division of the sample rate by the pre-defined bin size provides the data point. Further, the first processing unit 106 performs fast fourier transform (hereinafter “FFT”) on each bin size of the audio to obtain the one or more prominent frequencies and the one or more prominent amplitudes. The first processing unit 106 compares the one or more prominent frequencies and the one 20 or more prominent amplitudes with a stored one or more prominent frequencies and a stored one or more prominent amplitudes.
In an embodiment of the present disclosure, the media content broadcasted on another channel uses a pre-defined regional language in the audio. 25 In another embodiment of the present disclosure, the media content broadcasted on another channel uses a standard language accepted nationally.
In an embodiment of the present disclosure, the broadcast reception device 102 receives media content corresponding to the broadcasted content 30 having audio in the pre-defined regional language or the standard language. The media content corresponds to another channel.
Page 23 of 44
In an embodiment of the present disclosure, the first processing unit 106 extracts the first set of audio fingerprints and the first set of video fingerprints corresponding to another channel. The first processing unit 106 extracts the pre-defined number of prominent frames and generates pre-defined number of digital 5 signature values. The first processing unit 106 performs the temporal recurrence algorithm to detect a new advertisement. In an embodiment of the present disclosure, the first processing unit 106 generates prominent frequencies and prominent amplitudes of the audio. In another embodiment of the present disclosure, the first processing unit 106 discards the audio from the media content. 10 In an embodiment of the present disclosure, the first processing unit 106 probabilistically matches the one or more prominent frequencies with stored prominent frequencies in the first database 106a. The stored prominent frequencies and the stored prominent amplitudes correspond to a regional channel having audio in the pre-defined regional language or standard language. In an 15 embodiment of the present disclosure, the standard language is English. In another embodiment of the present disclosure, the first processing unit 106 gives precedence to results of probabilistic match of video fingerprints than to the audio fingerprints. In an embodiment of the present disclosure, the administrator 110 manually tags the detected advertisement broadcasted in the pre-defined regional 20 language or the standard language. In another embodiment of the present disclosure, the advertisement detection system 104 automatically tags the detected advertisement broadcasted in the pre-defined regional language or the standard language.
25
Going further, the first processing unit 106 fetches the corresponding video and audio clip associated to the probabilistically matched digital signature values. The first database 106a and the first processing unit 106 are associated with an administrator 110. The administrator 110 is associated with a display device and a control and input interface. In addition, the display device is 30 configured to display a graphical user interface (hereinafter “GUI”) of an installed
Page 24 of 44
operating system. The administrator 110 checks for the presence of the audio and the video clip manually in the master database 112. The administrator 110 decides whether the audio clip and the video clip correspond to a new advertisement. The administrator 110 tags each audio clip and the video clip with a tag. The tag corresponds to a brand name associated with a detected 5 advertisement. The administrator 110 stores the metadata of the probabilistically matched digital fingerprint values in the master database 112.
In addition, the first processing unit 106 reports a positively matched digital signature values corresponding to each detected advertisement in a 10 reporting database present in the first database 106a. The first processing unit 106 discards any detected advertisement already reported in the reporting database.
In an embodiment of the present disclosure, the second processing unit 108 performs the histogram normalization of each frame of the media content 15 broadcasted on the channel. The second processing unit 108 performs the histogram normalization. The second processing unit 108 sets each pixel value in each frame of the media content to a standard pixel value range set as a standard for each detected advertisement. In another embodiment of the present disclosure, the second processing unit 108 skips the histogram normalization. 20
In an embodiment of the present disclosure, the second processing unit 108 scales each frame of the media content to a pre-defined scale. In an embodiment of the present disclosure, the pre-defined scale of each frame is 640 by 480. In an embodiment of the present disclosure, the scaling of each frame is 25 done by trimming a first region corresponding to a channel logo and a second region corresponding to a channel’s dynamic ticker. In another embodiment of the present disclosure, the scaling of each frame is done by trimming the first region corresponding to the channel’s dynamic ticker and the second region corresponding to the channel logo. In another embodiment of the present 30 disclosure, the second processing unit 108 skips the scaling of each frame when each frame has the pre-defined scale.
Page 25 of 44
The second processing unit 108 includes a second central processing unit and associated peripherals for supervised detection of the one or more advertisements (also shown in FIG. 1C). The second processing unit 106 is connected to a second database 108a. The second processing unit 108 is 5 programmed to perform the extraction of the first set of audio fingerprints and the first set of video fingerprints corresponding to the media content broadcasted on the channel. The first set of video fingerprints and the first set of audio fingerprints are extracted sequentially in the real time. The extraction of the first set of video fingerprints is done by sequentially extracting the one or more 10 prominent fingerprints corresponding to the one or more prominent frames for the pre-defined interval of broadcast.
Furthermore, each of the one or more prominent fingerprints corresponds to the prominent frame having sufficient contrasting features 15 compared to the adjacent prominent frame. For example, let us suppose that the second processing unit 108 selects 6 prominent frames per second from 25 frames per second. Each pair of adjacent frames of the 6 prominent frames will have evident contrasting features. The second processing unit 108 generates the set of digital signature values corresponding to the extracted set of video fingerprints. 20 The second processing unit 108 generates each digital signature value of the set of digital signature values by dividing each prominent frame of the one or more prominent frames into the pre-defined number of blocks. In an embodiment of the present disclosure, the predefined number of block is 15 (4X4). In another embodiment of the present disclosure, the pre-defined number of blocks is any 25 suitable number. Each block of the pre-defined number of blocks has the pre-defined number of pixels. Each pixel is fundamentally the combination of R, G and B colors. The colors are collectively referred to as RGB. Each color of the pixel (RGB) has the pre-defined value in the pre-defined range of values. The predefined range of values is 0-255. 30
Page 26 of 44
The second processing unit 108 gray-scales each block of each prominent frame of the one or more prominent frames. The second processing unit 108 calculates the first bit value and the second bit value for each block of the prominent frame. The first bit value and the second bit value are calculated from comparison of the mean and the variance for the pre-defined number of pixels 5 with the corresponding mean and variance for the master frame. The master frame is present in the master database 112. The second processing unit 108 assigns the first bit value and the second bit with the binary 0 when the mean and the variance for each block is less the corresponding mean and variance of each master frame. The second processing unit 108 assigns the first bit value and the 10 second bit value with the binary 1 when the mean and the variance for each block is greater than the corresponding mean and variance of each master frame.
The second processing unit 108 obtains the 32 bit digital signature value corresponding to each prominent frame. The 32 bit digital signature value 15 is obtained by sequentially arranging the first bit value and the second bit value for each block of the pre-defined number of blocks of the prominent frame. The second processing unit 108 stores each digital signature value corresponding to each prominent frame of the one or more prominent frames in the second database 108a. The digital signature value corresponds to the one or more programs and 20 the one or more advertisements.
The second processing unit 108 performs the supervised detection of the one or more advertisements. The second processing unit 108 probabilistically matches a second pre-defined number of digital signature values with the stored 25 set of digital signature values present in the master database 112. The second pre-defined number of digital signature values corresponds to the second pre-defined number of prominent frames of the real time broadcasted media content. The probabilistic match is performed for the set of digital signature values by utilizing a sliding window algorithm. The second processing unit 108 determines the 30 positive match in the probabilistically matching of the second pre-defined number
Page 27 of 44
of digital signature values with the stored set of digital signature values. The stored set of digital signal values is present in the master database 112. In an embodiment of the present disclosure, the second pre-defined number of digital signature values of the set of digital signature values for the supervised detection of the one or more advertisements is 6. In another embodiment of the present 5 disclosure, the second pre-defined number of digital signature values is selected based on optimal processing capacity and performance of the second processing unit 108.
In an example, let us suppose that the second processing unit 108 10 stores 300 digital signature values corresponding to 300 prominent frames in the second database 108a for 10 seconds of the media content. The second processing unit 108 probabilistically matches 6 digital signature values corresponding to 101st to 107st prominent frame with each 6 digital signature values corresponding to 300 previously stored prominent frames. The 300 15 previously stored prominent frames are present in the master database 112.
In another example, suppose 300 digital signature values from 500th prominent frame to 800th prominent frame gives a positive match with a stored 150th frame to 450th frame in the master database 112. The second processing 20 unit 108 checks whether the number of positive matches is in the pre-defined range of positive matches and the positive matches correspond to media content in the first limiting duration and the second limiting duration. In addition, the second processing unit 108 checks whether the positive matches of 300 digital signature values for supervised detection of the one or more advertisements is in 25 the required sequence and order.
The second processing unit 108 checks for the degree of match of the pre-defined range of number of bits of the second pre-defined number of signature values. In an example, the degree of match of 192 bits of the generated set of 30 digital signature values with stored 192 digital signature values is 185 bits. In
Page 28 of 44
such case, the second processing unit 108 flags the probabilistic match as the positive match. In another example, the degree of match of 192 bits of the generated set of digital signature values with stored 192 digital signature values is 179 bits. In such case, the second processing unit 108 flags the probabilistic match as the negative match. In an embodiment of the present disclosure, the pre-5 defined range of number of bits is 0-12.
The second processing unit 108 compares the one or more prominent frequencies and the one or more prominent amplitudes with the stored one or more prominent frequencies and the stored one or more prominent amplitudes. The one or more prominent frequencies and the one or more prominent 10 amplitudes corresponding to the extracted first set of audio fingerprints. In an embodiment of the present disclosure, the administrator 110 manually checks whether each supervised advertisement detected is an advertisement or a program.
In an embodiment of the present disclosure, the second processing 15 unit 108 extracts the first set of audio fingerprints and the first set of video fingerprints corresponding to another channel. The second processing unit 108 extracts the pre-defined number of prominent frames and generates pre-defined number of digital signature values. The second processing unit 108 performs probabilistic matching of digital signature values corresponding to the video with 20 the stored digital signature values in the master database 112 to detect a repeated advertisement. In an embodiment of the present disclosure, the second processing unit 108 generates the one or more prominent frequencies of the audio. In another embodiment of the present disclosure, the second processing unit 108 discards the audio from the media content. In an embodiment of the present disclosure, the 25 master database 112 includes the one or more advertisements corresponding to a same advertisement in every regional language. In another embodiment of the present disclosure, the master database 112 includes the advertisement in a specific national language. In embodiment of the present disclosure, the second processing unit probabilistically matches the one or more prominent frequencies 30 with stored prominent frequencies. The stored prominent frequencies correspond
Page 29 of 44
to a regional channel having audio in the pre-defined regional language or standard language in the master database 112. In an embodiment of the present disclosure, the standard language is English. In another embodiment of the present disclosure, the second processing unit 108 gives precedence to results of probabilistic match of video fingerprints than to the audio fingerprints. 5
In an embodiment of the present disclosure, the advertisement detection system 104 reports a frequency of each advertisement broadcasted for a first time and a frequency of each advertisement broadcasted repetitively. In another embodiment of the present disclosure, the administrator 110 reports the 10 frequency of each advertisement broadcasted for the first time and the frequency of each advertisement broadcasted repetitively.
Further, the master database 112 is present in a master server. The master database 112 includes a plurality of digital video and audio fingerprint 15 records and every signature value corresponding to each previously detected and newly detected advertisement. The master database 112 is connected to the advertisement detection system 104. In an embodiment of the present disclosure, the master server is present in a remote location. In another embodiment of the present disclosure, the master server is present locally with the advertisement 20 detection system 104.
Further, the advertisement detection system 104 stores the generated set of digital signature values, the first set of audio fingerprints and the first set of video fingerprints in the first database 106a and the second database 108a. 25 Furthermore, the advertisement detection system 104 updates the first metadata manually in the master database 112 for the unsupervised detection of the one or more advertisements. The first metadata includes the set of digital signature values and the first set of video fingerprints.
30
It may be noted that in FIG. 1A, FIG. 1B and FIG. 1C, the system 100 includes the broadcast reception device 102 for decoding one channel;
Page 30 of 44
however, those skilled in the art would appreciate the system 100 includes more number of broadcast reception devices for decoding more number of channels. It may be noted that in FIG. 1A, FIG. 1B and FIG. 1C, the system 100 includes the advertisement detection system 104 for the supervised and the unsupervised detection of the one or more advertisement corresponding to one channel; 5 however, those skilled in the art would appreciate that the advertisement detection system 104 detects the one or more advertisements corresponding to more number of channels. It may be noted that in FIG. 1A, FIG. 1B and FIG. 1C, the administrator 110 manually checks each newly detected advertisement in the master database 112; however, those skilled in the art would appreciate that the 10 advertisement detection system 104 automatically checks for each advertisement in the master database 112.
FIG. 2 illustrates a block diagram 200 of the advertisement detection system 104, in accordance with various embodiments of the present disclosure. 15 The block diagram 200 describes the advertisement detection system 104 configured for the unsupervised and the supervised detection of the one or more advertisements.
The block diagram 200 of the advertisement detection system 104 20 includes an extraction module 202, a generation module 204, a storage module 206, a detection module 208 and an updating module 214. The extraction module 202 extracts the first set of audio fingerprints and the first set of video fingerprints corresponding to the media content broadcasted on the channel. The first set of audio fingerprints and the first set of video fingerprints are extracted sequentially 25 in the real time (as shown in detailed description of FIG. 1A).
Further, the generation module 204 generates the set of digital signature values corresponding to the extracted set of video fingerprints. The generation module 204 generates each digital signature value of the set of digital 30 signature values by dividing and grayscaling each prominent frame into the pre-defined number of blocks. Further, the generation module 204 calculates and
Page 31 of 44
obtains each digital signature value corresponding to each block of the prominent frame (as shown in detailed description of FIG. 1A). The generation module 204 includes a dividing module 204a, a grayscaling module 204b, a calculation module 204c and an obtaining module 204d. The dividing module 204a divides each prominent frame of the one or more prominent frames into the pre-defined 5 number of blocks (as shown in detailed description of FIG. 1A). The grayscaling module 204b grayscales each block of each prominent frame of the one or more prominent frames. The calculation module 204c calculates the first bit value and the second bit value for each block of the prominent frame (as described in the detailed description of FIG. 1A). The obtaining module 204d obtains the 32 bit 10 digital signature value corresponding to each prominent frame (as described in detailed description of FIG. 1A).
The storage module 206 stores the generated set of digital signature values, the first set of audio fingerprints and the first set of video fingerprints in 15 the first database 106a and the second database 108a (as described in detailed description of FIG. 1A). Further, the detection module 208 detects the one or more advertisements broadcasted on the channel. The detection module 208 includes an unsupervised detection module 210 and the supervised detection module 212. The unsupervised detection module 210 detects a new advertisement 20 through unsupervised machine learning. The unsupervised detection module 210 includes a matching module 210a, a comparison module 210b, a determination module 210c, a fetching module 210d, a checking module 210e and a reporting module 210f. The matching module 210a probabilistically matches the first pre-defined number of digital signature values corresponding to the pre-defined 25 number of prominent frames with the stored set of digital signature values (as described in detailed description of FIG. 1A).
Furthermore, the comparison module 210b compares the one or more prominent frequencies and the one or more prominent amplitudes of the extracted 30 first set of audio fingerprints (as described in detailed description of FIG. 1A).
Page 32 of 44
The determination module 210c determines the positive probabilistic match of the pre-defined number of prominent frames based on the pre-defined condition (as described in the detailed description of FIG. 1A). The fetching module 210d fetches the video and the audio clip corresponding to the probabilistically matched digital signature values (as described in the detailed description of FIG. 5 1A). Moreover, the checking module 210e checks presence of the audio and the video clip manually in the master database 112 (as described in detailed description of FIG. 1A). In addition, the reporting module 210f reports the positively matched digital signature values corresponding to the advertisement of the one or more advertisements in the reporting database present in the first 10 database 106a (as described in the detailed description of FIG. 1A).
The supervised detection module 212 includes a correlation module 212a, contrasting module 212b and a deduction module 212c. The correlation module 212a probabilistically matches the second pre-defined number of digital 15 signature values with the stored set of digital signature values present in the master database 112 (as described above in the detailed description of FIG. 1A). Further, the contrasting module 212b comparing the one or more prominent frequencies and the one or more prominent amplitudes with the stored one or more prominent frequencies and the stored one or more prominent amplitudes (as 20 described in the detailed description of FIG. 1A). The deduction module 212c determines the positive match in the probabilistically matching of the second pre-defined number of digital signature values with the stored set of digital signature values in the master database 112. In addition, the deduction module 212d determines the positive match from the comparison of the one or more prominent 25 frequencies with the stored one or more prominent frequencies (as described in the detailed description of FIG. 1A).
Going further, the updating module 214 updates the first metadata manually in the master database 112 for the unsupervised detection of the one or 30 more advertisements. The first metadata includes the set of digital signature
Page 33 of 44
values and the first set of video fingerprints corresponding to the detected advertisement (as described in the detailed description of FIG. 1A).
FIG. 3 illustrates a flow chart 300 for the unsupervised and the supervised detection of the one or more advertisements broadcasted on the 5 channel, in accordance with various embodiments of the present disclosure. It may be noted that to explain the process steps of the flowchart 300, references will be made to the interactive messaging system elements of the FIG. 1A, FIG. 1B, FIG. 1C and FIG. 2.
10
The flowchart 300 initiates at step 302. At step 304, the extraction module 202 extracts the first set of audio fingerprints and the first set of video fingerprints corresponding to the media content broadcasted on the channel. The first set of audio fingerprints and the first set of video fingerprints is extracted sequentially in the real time. At step 306, the generation module 204 generates 15 the set of digital signature values corresponding to the extracted set of video fingerprints. Further, at step 308, the detection module 208 detects the one or more advertisements broadcasted on the channel. The flow chart 300 terminates at step 312.
20
It may be noted that the flowchart 300 is explained to have above stated process steps; however, those skilled in the art would appreciate that the flowchart 300 may have more/less number of process steps which may enable all the above stated embodiments of the present disclosure.
25
FIG. 4 illustrates a block diagram of a communication device 400, in accordance with various embodiments of the present disclosure. The communication device 400 enables host process of the advertisement detection system 104. The communication device 400 includes a control circuitry module 402, a storage module 404, an input/output circuitry module 406, and a 30 communication circuitry module 408. The communication device 400 includes any suitable type of portable electronic device. The communication device 400
Page 34 of 44
includes but may not be limited to a personal e-mail device (e.g., a Blackberry.TM. made available by Research in Motion of Waterloo, Ontario), a personal data assistant ("PDA"), a cellular telephone. In addition, the communication device 400 includes a smartphone, the laptop, computer and the tablet. In another embodiment of the present disclosure, the communication 5 device 400 can be a desktop computer.
From the perspective of this disclosure, the control circuitry module 402 includes any processing circuitry or processor operative to control the operations and performance of the communication device 400. For example, the 10 control circuitry module 402 may be used to run operating system applications, firmware applications, media playback applications, media editing applications, or any other application.
In an embodiment of the present disclosure, the control circuitry 15 module 402 drives a display and process inputs received from the user interface. From the perspective of this disclosure, the storage module 404 includes one or more storage mediums. The one or more storage medium includes a hard-drive, solid state drive, flash memory, permanent memory such as ROM, any other suitable type of storage component, or any combination thereof. The storage 20 module 404 may store, for example, media data (e.g., music and video files), application data (e.g., for implementing functions on the communication device 400).
From the perspective of this disclosure, the I/O circuitry module 406 25 may be operative to convert (and encode/decode, if necessary) analog signals and other signals into digital data. In an embodiment of the present disclosure, the I/O circuitry module 406 may convert the digital data into any other type of signal and vice-versa. For example, the I/O circuitry module 406 may receive and convert physical contact inputs (e.g., from a multi-touch screen), physical movements 30 (e.g., from a mouse or sensor), analog audio signals (e.g., from a microphone), or any other input. The digital data may be provided to and received from the
Page 35 of 44
control circuitry module 402, the storage module 404, or any other component of the communication device 400.
It may be noted that the I/O circuitry module 406 is illustrated in FIG. 4 as a single component of the communication device 400; however those skilled 5 in the art would appreciate that several instances of the I/O circuitry module 406 may be included in the communication device 400.
The communication device 400 may include any suitable interface or component for allowing the user to provide inputs to the I/O circuitry module 406. 10 The communication device 400 may include any suitable input mechanism. Examples of the input mechanism include but may not be limited to a button, keypad, dial, a click wheel, and a touch screen. In an embodiment, the communication device 400 may include a capacitive sensing mechanism, or a multi-touch capacitive sensing mechanism. 15
In an embodiment of the present disclosure, the communication device 400 may include specialized output circuitry associated with output devices such as, for example, one or more audio outputs. The audio output may include one or more speakers built into the communication device 400, or an 20 audio component that may be remotely coupled to the communication device 400.
The one or more speakers can be mono speakers, stereo speakers, or a combination of both. The audio component can be a headset, headphones or ear buds that may be coupled to the communication device 400 with a wire or 25 wirelessly.
In an embodiment, the I/O circuitry module 406 may include display circuitry for providing a display visible to a user. For example, the display circuitry may include a screen (e.g., an LCD screen) that is incorporated in the 30 communication device 400.
Page 36 of 44
The display circuitry may include a movable display or a projecting system for providing a display of content on a surface remote from the communication device 400 (e.g., a video projector). In an embodiment of the present disclosure, the display circuitry may include a coder/decoder to convert digital media data into the analog signals. For example, the display circuitry may 5 include video Codecs, audio Codecs, or any other suitable type of Codec.
The display circuitry may include display driver circuitry, circuitry for driving display drivers or both. The display circuitry may be operative to display content. The display content can include media playback information, 10 application screens for applications implemented on the electronic device, information regarding ongoing communications operations, information regarding incoming communications requests, or device operation screens under the direction of the control circuitry module 402. Alternatively, the display circuitry may be operative to provide instructions to a remote display. 15
In addition, the communication device 400 includes the communication circuitry module 408. The communication circuitry module 408 may include any suitable communication circuitry operative to connect to a communication network. In addition, the communication circuitry module 408 20 may include any suitable communication circuitry to transmit communications (e.g., voice or data) from the communication device 400 to other devices. The other devices exist within the communications network. The communications circuitry 408 may be operative to interface with the communication network through any suitable communication protocol. Examples of the communication 25 protocol include but may not be limited to Wi-Fi, Bluetooth RTM, radio frequency systems, infrared, LTE, GSM, GSM plus EDGE, CDMA, and quadband.
In an embodiment, the communications circuitry module 408 may be 30 operative to create a communications network using any suitable communications protocol. For example, the communication circuitry module 408 may create a
Page 37 of 44
short-range communication network using a short-range communications protocol to connect to other devices. For example, the communication circuitry module 408 may be operative to create a local communication network using the Bluetooth, RTM protocol to couple the communication device 400 with a Bluetooth, RTM headset. 5
It may be noted that the computing device is shown to have only one communication operation; however, those skilled in the art would appreciate that the communication device 400 may include one more instances of the communication circuitry module 408 for simultaneously performing several 10 communication operations using different communication networks. For example, the communication device 400 may include a first instance of the communication circuitry module 408 for communicating over a cellular network, and a second instance of the communication circuitry module 408 for communicating over Wi-Fi or using Bluetooth RTM. 15
In an embodiment of the present disclosure, the same instance of the communications circuitry module 408 may be operative to provide for communications over several communication networks. In another embodiment of the present disclosure, the communication device 400 may be coupled to a host 20 device for data transfers and sync of the communication device 400. In addition, the communication device 400 may be coupled to software or firmware updates to provide performance information to a remote source (e.g., to providing riding characteristics to a remote server) or performing any other suitable operation that may require the communication device 400 to be coupled to the host device. 25 Several computing devices may be coupled to a single host device using the host device as a server. Alternatively or additionally, the communication device 400 may be coupled to the several host devices (e.g., for each of the plurality of the host devices to serve as a backup for data stored in the communication device 400). 30
Page 38 of 44
The present disclosure has numerous disadvantages over the prior art. The present disclosure provides a novel method to detect any new advertisement running for the first time on any television channel. The advertisements are detected robustly and dedicated supervised and unsupervised central processing unit (hereinafter “CPU”) are installed. Further, the present disclosure provides a 5 method and system that is economic and provides high return of investment. The detection of each repeated advertisement on supervised CPU and each new advertisement on unsupervised CPU significantly saves processing power and saves significant time. The disclosure provides a cost efficient solution to a scaled mapping and database for advertisement broadcast. 10
The foregoing descriptions of specific embodiments of the present technology have been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the present technology to the precise forms disclosed, and obviously many modifications and variations are possible in 15 light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the present technology and its practical application, to thereby enable others skilled in the art to best utilize the present technology and various embodiments with various modifications as are suited to the particular use contemplated. It is understood that various omissions and 20 substitutions of equivalents are contemplated as circumstance may suggest or render expedient, but such are intended to cover the application or implementation without departing from the spirit or scope of the claims of the present technology.
While several possible embodiments of the invention have been 25 described above and illustrated in some cases, it should be interpreted and understood as to have been presented only by way of illustration and example, but not by limitation. Thus, the breadth and scope of a preferred embodiment should not be limited by any of the above-described exemplary embodiments.
30
Page 39 of 44
CLAIMS We claim: 1. A computer-implemented method for detecting one or more advertisements broadcasted on a channel in real time, the computer-5 implemented method comprising: extracting, with a processor, a first set of audio fingerprints and a first set of video fingerprints corresponding to a media content broadcasting on the channel, wherein the set of audio fingerprints and the first set of video fingerprints being extracted sequentially in the real time; 10 generating, with the processor, a set of digital signature values corresponding to an extracted set of video fingerprints, and detecting, with the processor, the one or more advertisements broadcasted on the channel. 15 2. The computer-implemented method as recited in claim 1, further comprising storing, with the processor, the generated set of digital signature values, the first set of audio fingerprints and the first set of video fingerprints in a first database and a second database. 20 3. The computer-implemented method as recited in claim 1, wherein the extraction of the first set of video fingerprints being done by sequentially extracting one or more prominent fingerprints corresponding to one or more prominent frames of a pre-defined number of frames present in the media content for a pre-defined interval of broadcast. 25
4. The computer-implemented method as recited in claim 1, wherein the generating of each digital signature value of the set of digital signature values being done by:
Page 40 of 44
dividing each prominent frame of the one or more prominent frames into a pre-defined number of blocks, wherein each block of the pre-defined number of block having a pre-defined number of pixels; grayscaling each block of each prominent frame of the one or more prominent frames; 5 calculating a first bit value and a second bit value for each block of the prominent frame, wherein the first bit value and the second bit value being calculated from comparing a mean and a variance for the pre-defined number of pixels in each block of the prominent frame with a corresponding mean and variance for a master frame in a master database; 10 and obtaining a 32 bit digital signature value corresponding to each prominent frame, wherein the 32 bit digital signature value being obtained by sequentially arranging the first bit value and the second bit value for each block of the pre-defined number of blocks of the prominent frame. 15 5. The computer-implemented method as recited in claim 4, wherein the first bit value and the second bit value being assigned a binary 0 when the mean and the variance for each block of the prominent frame being less the corresponding mean and variance of each master frame. 20 6. The computer-implemented method as recited in claim 4, wherein the first bit value and the second bit value being assigned a binary 1 when the mean and the variance for each block of the prominent frame being greater than the corresponding mean and variance of each master frame. 25
7. The computer-implemented method as recited in claim 1, wherein a detection of the one or more advertisements being a supervised detection and an unsupervised detection.
30 8. The computer-implemented method as recited in claim 7, wherein the unsupervised detection of the one or more advertisements being done by:
Page 41 of 44
probabilistically matching a first pre-defined number of digital signature values corresponding to a pre-defined number of prominent frames of a real time broadcasted media content with a stored set of digital signature values present in a first database, wherein the probabilistic match being performed for the set of digital signature values by utilizing a 5 sliding window algorithm; comparing one or more prominent frequencies and one or more prominent amplitudes of an extracted first set of audio fingerprints; determining a positive probabilistic match of the pre-defined number of prominent frames based on a pre-defined condition; 10 fetching a video and an audio clip corresponding to the probabilistically matched digital signature values; and checking presence of the audio and the video clip manually in a master database; and reporting a positively matched digital signature values 15 corresponding to an advertisement of the one or more advertisements in a reporting database present in the first database. 9. The computer-implemented method as recited in claim 8, wherein the pre-defined condition comprises a pre-defined range of positive matches 20 corresponding to probabilistically matched digital signature values, a pre-defined duration of media content corresponding to the positive match, a sequence and an order of the positive matches and a degree of match of a pre-defined range of number of bits of the first pre-defined number of signature values. 25 10. The computer-implemented method as recited in claim 8, wherein the first pre-defined number of digital signature values of the set of digital signature values for the unsupervised detection of the one or more advertisements being 20. 30
Page 42 of 44
11. The computer-implemented method as recited in claim 1, further comprising, updating, with the processor, a first metadata comprising the set of digital signature values and the first set of video fingerprints corresponding to a detected advertisement manually in a master database for an unsupervised detection. 5
12. The computer-implemented method as recited in claim 7, wherein the supervised detection of the one or more advertisements being done by: probabilistically matching a second pre-defined number of digital signature values corresponding to a pre-defined number of prominent 10 frames of a real time broadcasted media content with a stored set of digital signature values present in a master database, wherein probabilistic match being performed for the set of digital signature values by utilizing a sliding window algorithm; comparing one or more prominent frequencies and one or more 15 prominent amplitudes corresponding to the extracted first set of audio fingerprints with a stored one or more prominent frequencies and a stored one or more prominent amplitudes; and determining a positive match in the probabilistically matching of the second pre-defined number of digital signature values with the stored 20 set of digital signature values in the master database and comparing of the one or more prominent frequencies and one or more prominent amplitudes corresponding to an extracted first set of audio fingerprints with the stored one or more prominent frequencies and the stored one or more prominent amplitudes. 25 13. The computer-implemented method as recited in claim 13, wherein the second pre-defined number of digital signature values of the set of digital signature values for the supervised detection of the one or more advertisements being 6.
| # | Name | Date |
|---|---|---|
| 1 | Form 5 [09-03-2016(online)].pdf | 2016-03-09 |
| 2 | Form 3 [09-03-2016(online)].pdf | 2016-03-09 |
| 3 | Drawing [09-03-2016(online)].pdf | 2016-03-09 |
| 4 | Description(Complete) [09-03-2016(online)].pdf | 2016-03-09 |
| 5 | abstract.jpg | 2016-07-14 |
| 6 | 201611008283-GPA-(19-07-2016).pdf | 2016-07-19 |
| 7 | 201611008283-Form-1-(19-07-2016).pdf | 2016-07-19 |
| 8 | 201611008283-Correspondence Others-(19-07-2016).pdf | 2016-07-19 |
| 9 | Form 26 [11-04-2017(online)].pdf | 2017-04-11 |
| 10 | 201611008283-Proof of Right (MANDATORY) [15-11-2017(online)].pdf | 2017-11-15 |
| 11 | 201611008283-OTHERS-161117.pdf | 2017-11-24 |
| 12 | 201611008283-Correspondence-161117.pdf | 2017-11-24 |