System for authenticating digital content

Abstract

A system for authenticating digital content, comprising: a computing platform having a hardware processor and a memory storing software code. According to one embodiment, the hardware processor executes the software code to: receive digital content; identify an image of a person depicted in the digital content; determine ear shape parameters of the person depicted in the image; determine another biometric parameter of the person depicted in the image; and calculate a ratio of the ear shape parameters of the person depicted in the image to the biometric parameter of the person depicted in the image. The hardware processor is further configured to execute the software code to: perform a comparison of the calculated ratio with a predetermined value; and determine whether the person depicted in the image is a true depiction of the person based on the comparison of the calculated ratio with the predetermined value.

Description

BACKGROUND OF THE INVENTION

[0001] Advances in machine learning have enabled the creation of realistic but fake reproductions of a person's image or voice, known as "deepfakes," through the use of deep artificial neural networks. Deepfakes can be created without the consent of the person whose image or voice is used and may make the person represented appear to have said or done things they actually did not say or do. Thus, digitally manipulated content using deepfakes can be maliciously used to spread misinformation.

[0002] Due to the widespread popularity of digital content in entertainment and news distribution, effective authentication and management of such content are important for its creators, owners, and distributors. However, with the continuous improvement of machine learning solutions, deepfakes are and will continue to be difficult to detect. As a result, in violation of contractual agreements or regulatory restrictions, digitally manipulated or even completely fake content may be inadvertently played or otherwise distributed, exposing content owners and / or distributors to potential legal risks. SUMMARY OF THE INVENTION

[0003] Systems for authenticating digital content are provided herein, substantially as shown in and / or described in conjunction with at least one of the figures, and more fully set forth in the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0004] Figure 1 A schematic diagram of an exemplary system for authenticating digital content according to one embodiment is shown;

[0005] Figure 2 Another exemplary embodiment of a system for authenticating digital content is shown;

[0006] Figure 3 Shown is applicable to Figure 1 and Figure 2 An example diagram of authenticity analysis software code executable by a hardware processor of the system shown;

[0007] Figure 4 Is a flowchart representing an exemplary method used by a system for authenticating digital content according to one embodiment;

[0008] Figure 5 Is a flowchart representing an exemplary method used by a system for authenticating digital content according to another embodiment; and

[0009] Figure 6 Is a flowchart representing an exemplary method used by a system for authenticating digital content according to yet another embodiment. DETAILED DESCRIPTION

[0010] The following description includes specific information related to embodiments in the present disclosure. Those skilled in the art will recognize that the present disclosure can be implemented in ways different from those specifically discussed herein. The accompanying drawings and the accompanying detailed description in this application are directed only to exemplary embodiments. Unless otherwise specified, the same or corresponding elements in the drawings can be denoted by the same or corresponding reference numerals. In addition, the drawings and illustrations in this application are generally not drawn to scale and are not intended to correspond to actual relative sizes.

[0011] This application discloses a system for authenticating digital content, which overcomes the disadvantages and deficiencies in the prior art. It should be noted that in some embodiments, this content authentication solution can be executed by a substantially automated system as a substantially automated process. It should be noted that as used in this application, the terms "automation", "automated", and "automated operation" refer to systems and processes that do not require the participation of a human user (such as a system administrator). Although in some embodiments, a human system operator or administrator may check the authenticity determination made by the automated systems described herein, the human participation is optional. Therefore, the methods described in this application can be executed under the control of the hardware processing components of the disclosed automated systems.

[0012] Figure 1 A schematic diagram of an exemplary system for authenticating digital content according to one embodiment is shown. As described below, system 100 can be implemented using a computer server accessible via a local area network (LAN), or can be implemented as a cloud-based system. As Figure 1 shown, system 100 includes: a computing platform 102 having a hardware processor 104; a system memory 106 implemented as a non-transitory storage device; and a display 108. According to this exemplary embodiment, the system memory 106 stores: a biometric database 120 including biometric profiles 122a and 122b; a language database 124 including language profiles 126a and 126b and scripts 127a and 127b; and authenticity analysis software code 110 that provides an authenticity determination 138 regarding digital content 136.

[0013] Similarly, as Figure 1As shown, system 100 is implemented in the following usage environment, which includes: a communication network 130 having a network communication link 132; and, a user system 140 including a display 148. User 128 interacts with system 100 by using user system 140. It should be noted that communication network 130 and network communication link 132 enable: system 100 to receive digital content 136 provided by content contributor 134 or user 128, and output an authenticity determination 138 for presentation on display 148 of user system 140. Alternatively, or additionally, in some embodiments, authenticity determination 138 may be presented on display 108 of system 100.

[0014] Generally speaking, system 100 may be implemented as a quality control (QC) resource for a media entity that provides audio - video (AV) content in a linear television (TV) program stream. The media entity, for example, includes: a high - definition (HD) or ultra - HD (UHD) baseband video signal with embedded audio, subtitles, timecodes, and other auxiliary metadata (such as ratings and / or parental guidelines). Alternatively, or additionally, the media entity including system 100 as a QC resource may distribute AV content via radio or satellite radio broadcast.

[0015] According to Figure 1 In the exemplary embodiment shown, system 100 is configured to: receive digital content 136 from content contributor 134 or user system 140, and use authenticity analysis software code 110 executed by hardware processor 104 to determine the authenticity of digital content 136. Content contributor 134 may be another media entity, a professional news gatherer, or an amateur content contributor; a professional news gatherer, for example, is an authorized on - site reporter of the media entity including system 100; an amateur content contributor may provide digital content 136 in the form of home videos or other AV content generated using a personal communication device or other communication system. In some embodiments, content contributor 134 may utilize such a communication system to submit digital content 136 to system 100 via communication network 130 and network communication link 132. However, in other embodiments, content contributor 134 may utilize a communication system to submit digital content 136 to user system 140 utilized by user 128. In those latter embodiments, user 128 may further utilize user system 140 to submit digital content 136 to system 100 for authenticity determination, or, may use user system 140 to perform authenticity determination, as discussed in more detail below.

[0016] The digital content 136 may take the form of video content without audio, audio content without video, or AV content, such as: movies; serialized content including TV series, web series, and / or video blogs; sports content; news content; advertising content, or video game content, etc. Alternatively, in some embodiments, the digital content 136 may take the form of digital photos.

[0017] It should be noted that although, for conceptual clarity, this application refers to storing the authenticity analysis software code 110, the biometric database 120, and the language database 124 in the system memory 106, more generally, the system memory 106 may take the form of any computer-readable non-transitory storage medium. The expression "computer-readable non-transitory storage medium" as used in this application refers to any medium that does not include a carrier wave or other transitory signals that provide instructions to the hardware processor 104 of the computing platform 102 or the hardware processor of the user system 140 ( Figure 1 the hardware processor of the user system 140 is not shown). Thus, the computer-readable non-transitory medium may correspond to various types of media, such as volatile media and non-volatile media. Volatile media may include dynamic memory, such as dynamic random access memory (dynamic RAM); and non-volatile memory may include optical, magnetic, or electrostatic storage devices. Common forms of computer-readable non-transitory media include, for example, optical discs, RAM, programmable read-only memory (PROM), erasable PROM (EPROM), and flash memory.

[0018] It should also be noted that although Figure 1 the authenticity analysis software code 110, the biometric database 120, and the language database 124 are depicted as being co-located in the system memory 106, this representation is also provided merely for conceptual clarity. More generally, the system 100 may include one or more computing platforms 102, such as computer servers; they may be located in the same location, or, alternatively, may form an interconnected but distributed system, such as a cloud-based system.

[0019] As a result, the hardware processor 104 and the system memory 106 may correspond to distributed processor and memory resources within the system 100. Thus, it should be understood that various features of the biometric database 120 and / or the language database 124, as well as the authenticity analysis software code 110 (such as one or more features described below with reference to Figure 3 ), may be stored and / or executed using the distributed memory and / or processor resources of the system 100.

[0020] According to Figure 1In the illustrated embodiment, user 128 may utilize user system 140 to interact with system 100 via communication network 130 to determine the authenticity of digital content 136. In one such embodiment, computing platform 102 may correspond to one or more network-based computer servers accessible via a packet-switched network such as the Internet. Alternatively, computing platform 102 may correspond to one or more computer servers supporting a wide area network (WAN), a local area network (LAN), or included in another type of limited distribution or private network.

[0021] It should also be noted that although Figure 1 user system 140 is depicted as a mobile communication device, such as a smartphone or a tablet computer, this representation is also merely exemplary. More generally, user system 140 may be any suitable system that implements sufficient data processing capabilities to provide a user interface, support a connection to communication network 130, and implement the functions ascribed to user system 140 herein. In other embodiments, user system 140 may take the form of a desktop computer, a laptop computer, a gaming console, or a smart device such as a smart TV, and so on.

[0022] Regarding display 148 of user system 140, display 148 may be physically integrated with user system 140, or may be communicatively connected to user system 140 but physically separated from user system 140. For example, in the case where user system 140 is implemented as a smartphone, a laptop computer, a tablet computer, or a smart TV, display 148 will typically be integrated with user system 140. In contrast, in the case where user system 140 is implemented as a desktop computer, display 148 may take the form of a monitor separated from user system 140 in the form of a computer tower device. Similarly, as Figure 1 shown, display 108 of system 100 may be physically integrated with computing platform 102 of system 100, or may be communicatively connected to computing platform 102 but physically separated from computing platform 102. Displays 108 and 148 may be implemented as liquid crystal displays (LCDs), light-emitting diode (LED) displays, organic light-emitting diode (OLED) displays, or any other suitable display screen that performs a physical conversion of signals to light.

[0023] Figure 2 Another exemplary embodiment of a system for authenticating digital content is shown. According to Figure 2In the exemplary embodiment shown, user system 240 is communicatively connected to system 200 via network communication link 232. The computing platform 202 of system 200 includes a hardware processor 204 and a system memory 206, and the system memory 206 stores: a biometric database 220 including biometric profiles 222a and 122b; a language database 224 including language profiles 226a and 126b and scripts 227a and 127b; and authenticity analysis software code 210a that provides authenticity determination 238. Additionally, Figure 2 a display 208 of system 200 is shown.

[0024] As Figure 2 shown, system 240 includes: a computing platform 242 having a transceiver 243, a hardware processor 244, and a memory 246; and the memory 246 is implemented as a non-transitory storage device storing authenticity analysis software code 210b. According to Figure 2 the exemplary embodiment shown, authenticity analysis software code 210b provides authenticity determination 238 for presentation on a display 248 of user system 240. It should be noted that authenticity determination 238 may share any corresponding characteristics attributable to authenticity determination 138 in this disclosure Figure 1 herein.

[0025] Network communication link 232 and system 200 including a computing platform 202 having a hardware processor 204, a system memory 206, and a display 208 generally correspond to Figure 1 network communication link 132 and system 100 including a computing platform 102 having a hardware processor 104, a system memory 106, and a display 108 in this disclosure. Additionally, authenticity analysis software code 210a, biometric database 220, and language database 224 generally correspond to Figure 1 authenticity analysis software code 110, biometric database 120, and language database 124 in this disclosure. Thus, biometric database 220, language database 224, and authenticity analysis software code 210a may share any corresponding characteristics attributable to biometric database 120, language database 124, and authenticity analysis software code 110 in this disclosure, and vice versa.

[0026] Additionally, biometric profiles 222a and 222b included in biometric database 220, language profiles 226a and 226b stored in language database 224, and scripts 227a and 227b stored in language database 224 generally correspond to Figure 1Biometric profiles 122a and 122b, language profiles 126a and 126b, and scripts 127a and 127b therein. That is, biometric profiles 222a and 222b, language profiles 226a and 226b, and scripts 227a and 227b can share any corresponding features attributed to biometric profiles 122a and 122b, language profiles 126a and 126b, and scripts 127a and 127b in this disclosure, and vice versa.

[0027] Figure 2 The user system 240 and the display 248 in therein generally correspond to Figure 1 the user system 140 and the display 148 in therein, and the corresponding features can share any features attributed to any corresponding feature of this disclosure. Thus, similar to the user system 140, the user system 240 can take the form of, for example, a smart TV, a desktop computer, a laptop computer, a tablet computer, a game console, or a smartphone. Additionally, although Figure 1 not shown in therein, the user system 140 can include a plurality of features corresponding to the computing platform 242, the transceiver 243, the hardware processor 244, and the memory 246 storing the authenticity analysis software code 210b. Further, similar to the displays 108 and 148, the corresponding displays 208 and 248 can be implemented as LCD, LED displays, OLED displays, or any other suitable display screen that performs the physical conversion of signals to light.

[0028] The transceiver 243 can be implemented as a wireless communication unit such that the user system 240 can exchange data with the computing platform 202 via the network communication link 232. For example, the transceiver 243 can be implemented as a fourth-generation (4G) wireless transceiver, or as a 5G wireless transceiver configured to meet the IMT-2020 requirements established by the International Telecommunication Union (ITU). Regarding the authenticity analysis software code 210b, in conjunction with Figure 2 and with reference to Figure 1 , it should be noted that in some embodiments, the authenticity analysis software code 210b can be a thin client application that is only available for submitting digital content 136 to the system 100 / 200 and for presenting the authenticity determination 138 / 238 received from the system 100 / 200.

[0029] However, in other embodiments, the authenticity analysis software code 210b can be a software application that includes all the features of the authenticity analysis software code 210a and is capable of performing all the same functions. That is, in some embodiments, the authenticity analysis software code 210b corresponds to Figure 1 the authenticity analysis software code 110 in therein, and can share any features attributed to the corresponding features of this disclosure.

[0030] According to Figure 2 the exemplary embodiment shown, the authenticity analysis software code 210b is located in the memory 246 and is received by the user system 240 from the computing platform 202 or an authorized third-party source of the authenticity analysis software code 210b via the network communication link 232. In one embodiment, the network communication link 232 enables the authenticity analysis software code 210b to be transmitted through a packet-switched network (such as the Internet).

[0031] Once transmitted, for example, downloaded through the network communication link 232, the authenticity analysis software code 210b can be permanently stored in the memory 246 and can be locally executed by the hardware processor 244 on the user system 240. For example, the hardware processor 244 can be the central processing unit (CPU) of the user system 240, where the hardware processor 244 runs the operating system of the user system 240 and executes the authenticity analysis software code 210b.

[0032] It should be noted that, as Figure 1 shown, in some embodiments, the computing platform 102 of the system 100 for authenticating digital content can take the form of one or more network-based computer servers. However, as Figure 2 shown, in other embodiments, the user system 240 can be configured to provide substantially all the functions of the system 200. Therefore, in some embodiments, the computing platform of the system for authenticating digital content can be provided by the computing platform 242 of the user system 240. That is, in some embodiments, the computing platform 242 of the user system 240 for authenticating digital content can take the form of a computing platform of a mobile communication device, such as a smartphone or a tablet computer.

[0033] Figure 3 An example diagram of the authenticity analysis software code 310 suitable for execution by the hardware processor 104 / 204 of the system 100 / 200 or the hardware processor 244 of the user system 240 according to one embodiment is shown. As Figure 3 shown, the authenticity analysis software code 310 can include: a content reception and recognition module 312, a biometric comparison module 314, a language comparison module 316, and an authentication module 318. In addition, Figure 3 the received digital content 336 is shown as an input to the authenticity analysis software code 310, input to the biometric comparison 354, the language habit comparison 356, and the monologue or dialogue comparison 358, and the authenticity determination 338 as the output of the authenticity analysis software code 310. Figure 3Also shown is a biometric database 320 including biometric profiles 322a and 322b, and a language database 324 including language profiles 326a and 326b and scripts 327a and 327b.

[0034] Digital content 336 generally corresponds to Figure 1 the digital content 136 in Figure 3 and the corresponding features may share any characteristics attributable to any feature of the present disclosure. Figure 1 and Figure 2 the authenticity determination 338, biometric database 320, biometric profiles 322a and 322b, language database 324, language profiles 326a and 326b, and scripts 327a and 327b in

[0035] Figure 3 generally correspond to Figure 1 and 2 the authenticity determination 138 / 238, biometric database 120 / 220, biometric profiles 122a / 222a and 122b / 222b, language database 124 / 224, language profiles 126a / 226a and 126b / 226b, and scripts 127a / 227a and 127b / 227b in Figure 2 and may share any characteristics attributable to the corresponding features of the present disclosure. In other words, the authenticity analysis software code 110 / 210a and the authenticity analysis software code 210b may share any characteristics attributable to the authenticity analysis software code 310 of the present disclosure, and vice versa. Thus, similar to the authenticity analysis software code 310, the authenticity analysis software code 110 / 210a and the authenticity analysis software code 210b may include multiple modules corresponding to a content reception and recognition module 312, a biometric comparison module 314, a language comparison module 316, and an authentication module 318, respectively.

[0036] will be described further in connection with Figure 1 and Figure 2 and Figure 3 and with reference to Figure 4 and Figure 5 and Figure 6 the functions of the authenticity analysis software code 110 / 210a / 310 and the authenticity analysis software code 210b / 310. Figure 4 is a flowchart 460 representing an exemplary method used by a system for authenticating digital content according to one embodiment; and Figure 5FIG. 570 is a flow chart representing an exemplary method used by a system for authenticating digital content according to another embodiment. Figure 6 FIG. 680 is a flow chart representing an exemplary method used by a system for authenticating digital content according to yet another embodiment. With respect to Figure 4 、 Figure 5 and Figure 6 the methods outlined in, it should be noted that, in order not to confuse the discussion of the inventive features in this application, certain details and features have been omitted from the respective flow charts 460, 570 and 680.

[0037] In conjunction with Figure 1 、 Figure 2 and Figure 3 and with reference to Figure 4 , flow chart 460 begins with: receiving digital content 136 / 336 (act 461). As described above, in some embodiments, the digital content 136 / 136 may take the form of video content without audio or AV content, such as: movies; serialized content including television series, web series and / or video blogs; sports content; news content; advertising content or video game content, etc. Alternatively, in some embodiments, the digital content 136 may take the form of digital photos.

[0038] As Figure 1 shown, in one embodiment, the system 100 may receive the digital content 136 from the content contributor 134 or the user system 140 via the communication network 130 and the network communication link 132. In those embodiments, the digital content 136 / 336 may be received by the authenticity analysis software code 110 / 210a / 310, which is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the content receiving and identifying module 312. However, in conjunction with Figure 1 with reference Figure 2 to, in another embodiment, the user system 140 / 240 may receive the digital content 136 / 336 from the content contributor 134 using the transceiver 243. In those embodiments, the digital content 136 / 336 may be received by the authenticity analysis software code 210b / 310, which is executed by the hardware processor 244 of the user system 140 / 240 and uses the content receiving and identifying module 312.

[0039] The flowchart 460 continues by identifying an image of a person depicted in the digital content 136 / 336 (action 462). In some embodiments, the digital content 136 / 336 can be a digital photograph, video, or AV content that includes an image of a well-known person (e.g., a celebrity athlete, actor, or politician). However, more generally, the person depicted in the digital content 136 / 336 and identified in action 462 can be anyone with one or more corresponding biometric profiles (e.g., biometric profiles 122a / 222a / 322a and / or biometric profiles 122b / 222b / 322b stored in the biometric database 120 / 220 / 320). For example, such a person can be an actor, journalist, news anchor, or other talent employed by a media entity that includes the system 100 / 200 as a QC resource.

[0040] It should be noted that the same person may have multiple biometric profiles stored in the biometric database 120 / 220 / 320. For example, as an actor ages, they may have different biometric profiles at different stages of their career. Alternatively, or additionally, an actor may have different biometric profiles for each role they play or each movie or other AV feature they participate in. Further, in some embodiments, it may be advantageous or desirable for a person to have multiple biometric profiles, each focusing on one or more specific biometric parameters. That is, for example, the same person may have a first biometric profile for ear shape parameters that changes over time, a second biometric profile for eye shape parameters that changes over time, a third biometric profile for facial symmetry that changes over time, and so on.

[0041] In embodiments where the system 100 / 200 receives the digital content 136 / 336 in action 461, the identification of the person depicted in the image included in the digital content 136 / 336 can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the content reception and identification module 312. However, in embodiments where the user system 140 / 240 receives the digital content 136 / 336 in action 461, the identification of the person depicted in the image included in the digital content 136 / 336 can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the content reception and identification module 312.

[0042] Flowchart 460 continues by determining ear shape parameters of the person depicted in the image and identified in action 462 (action 463). The ear shape parameters determined in action 463 can be a single parameter (e.g., a single dimension of the ear of the person depicted in the image) or a combination of ear dimensions (e.g., the sum of two or more ear dimensions, or a hash value of two or more ear dimensions). The ear size associated with the ear shape parameters determined in action 463 can include ear length (i.e., the distance from the top of the ear to the bottom of the ear), ear width in a direction perpendicular to the ear length, earlobe shape (e.g., pointed, rounded, square), and / or the angle of rotation of the ear relative to one or more cranial landmarks of the person depicted in the image. It should be noted that ear shape parameters can be particularly useful for authenticating identity because ear shapes can be very unique and different for different individuals.

[0043] In an implementation where the system 100 / 200 receives the digital content 136 / 336 in action 461, the determination of the ear shape parameters of the person depicted in the image and identified in action 462 can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the biometric comparison module 314. However, in an implementation where the user system 140 / 240 receives the digital content 136 / 336 in action 461, the determination of the ear shape parameters of the person depicted in the image and identified in action 462 can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the biometric comparison module 314.

[0044] Flowchart 460 continues by determining biometric parameters of the person depicted in the image and identified in action 462, where the biometric parameters are different from the above-described ear shape parameters (action 464). In some implementations, the biometric parameters determined in action 464 can be a single facial parameter, such as the interpupillary distance (hereinafter referred to as "IPD") of the person depicted in the image, or mouth shape or eye shape parameters. However, in other implementations, the biometric parameters determined in action 464 can be a combination of such facial parameters, such as the sum of two or more facial parameters, or a hash value of two or more facial parameters.

[0045] In an implementation where the system 100 / 200 receives the digital content 136 / 336 in operation 461, the determination of the biometric parameters of the person depicted in the image and identified in operation 462 can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the biometric comparison module 314. However, in an implementation where the user system 140 / 240 receives the digital content 136 / 336 in operation 461, the determination of the biometric parameters of the person depicted in the image identified in operation 462 can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the biometric comparison module 314.

[0046] Flowchart 460 continues with the calculation of the ratio (operation 465) of the ear shape parameters of the person depicted in the image determined in operation 463 to the biometric parameters of the person depicted in the image determined in operation 464. The ratio calculated in operation 465 can be expressed as a dimensionless, pure numerical ratio, as a ratio including dimensional units, or as a hash value. In an implementation where the system 100 / 200 receives the digital content 136 / 336 in operation 461, the calculation of the ratio of the ear shape parameters of the person depicted in the image to the biometric parameters of the person depicted in the image can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the biometric comparison module 314. However, in an implementation where the user system 140 / 240 receives the digital content 136 / 336 in operation 461, the calculation of the ratio of the ear shape parameters of the person depicted in the image to the biometric parameters of the person depicted in the image can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the biometric comparison module 314.

[0047] For example, the biometric comparison module 314 can include multiple feature classifiers implemented using a neural network (NN), such as an ear classifier and other biometric classifiers. These classifiers can be trained with ears and other biometric features, and in the case of the ear classifier, each NN will learn features to distinguish samples, such as ear length, ear width, earlobe shape, etc. To compare ears, for example, the feature vectors of each ear sample can be calculated and the distance between these vectors. The more similar one ear sample is to another, the closer the distance between their respective feature vectors.

[0048] The flowchart 460 continues by comparing the ratio calculated in operation 465 with a predetermined value (operation 466). For example, in the case where the person identified as being depicted in the image is an actor, journalist, news anchor, or other talent employed by a media entity that includes the system 100 / 200 as a QC resource, a predetermined value of the ratio calculated in operation 465 can be stored in the biometric database 120 / 220 / 320 for each such individual, for example, as part of one of the biometric profiles 122a / 222a / 322a or 122b / 222b / 322b.

[0049] In an implementation where the system 100 / 200 receives the digital content 136 / 336 in operation 461, the comparison of the ratio calculated in operation 465 with the predetermined value stored in the biometric database 120 / 220 / 320 can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the biometric comparison module 314. However, in an implementation where the user system 140 / 240 receives the digital content 136 / 336 in operation 461, the comparison of the ratio calculated in operation 465 with the predetermined value stored in the biometric database 120 / 220 / 320 can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the biometric comparison module 314. For example, in those latter implementations, the user system 140 / 240 can utilize the transceiver 243 and the communication network 130 to access the biometric database 120 / 220 / 320 stored on the computing platform 102 / 202 of the system 100 / 200. It should be noted that operation 466 causes the biometric comparison 354 to be provided as an input to the authentication module 318 of the authenticity analysis software code 110 / 210a / 310 or the authenticity analysis software code 210b / 310 by the biometric comparison module 314.

[0050] The exemplary method outlined in flowchart 460 can end with: determining whether the person depicted in the image is a true depiction of that person (action 467) based on a biometric comparison 354 of the ratio calculated in action 465 with a predetermined value stored in the biometric database 120 / 220 / 320. For example, in the case where the biometric comparison 354 shows a match between the ratio calculated in action 465 and the predetermined value stored in the biometric database 120 / 220 / 320, the authenticity determination 138 / 238 / 338 identifies the person depicted in the image as a true depiction of that person. Additionally, in some embodiments, action 467 can include: determining that the digital content 136 / 336 is authentic when, based on the comparison of the calculated ratio with the predetermined value, it is determined that the person depicted in the image is a true depiction of that person.

[0051] It should be noted that, as defined for the purposes of this disclosure, the term "match" refers to the result of a comparison of values that are substantially the same or similar within a predetermined tolerance. As a specific example, in the case of a tolerance of a predetermined ten percent (10%) variance, a "match" between the ratio calculated in action 465 and the predetermined value stored in the biometric database 120 / 220 / 320 can occur whenever the ratio calculated in action 465 is between 90% and 110% of the predetermined value stored in the biometric database 120 / 220 / 320.

[0052] In embodiments where the system 100 / 200 receives the digital content 136 / 336 in action 461, action 467 can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the authentication module 318 to output the authenticity determination 138 / 238 / 338. However, in embodiments where the user system 140 / 240 receives the digital content 136 / 336 in action 461, action 467 can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the authentication module 318 to output the authenticity determination 138 / 238 / 338.

[0053] It should be noted that, in some embodiments, the hardware processor 104 / 204 can execute the authenticity analysis software code 110 / 210a / 310, or the hardware processor 244 of the user system 140 / 240 can execute the authenticity analysis software code 210b / 310, to perform actions 461, 462, 463, 464, 465, 466, and 467 in an automated process that can omit human participation.

[0054] Now, in combination with Figure 1 , Figure 2 and Figure 3 and with reference to Figure 5 , as described above, Figure 5 FIG. 570 shows a flowchart of an exemplary method used by a system for authenticating digital content according to another embodiment. Flowchart 570 begins with: receiving digital content 136 / 336 having an audio track that includes a monologue and / or dialogue (act 571). As described above, in some embodiments, the digital content 136 / 136 may take the form of AV content, such as: movies; serialized content including TV show series, web series, and / or video blogs; sports content; news content; advertising content or video game content having an audio track that includes a monologue and / or dialogue, and so on.

[0055] As Figure 1 shown, in one embodiment, the system 100 may receive digital content 136 from a content contributor 134 or a user system 140 via a communication network 130 and a network communication link 132. In those embodiments, the digital content 136 / 336 may be received by authenticity analysis software code 110 / 210a / 310, which is executed by a hardware processor 104 / 204 of a computing platform 102 / 202 and uses a content reception and recognition module 312. However, in combination Figure 1 and with reference Figure 2 to, in another embodiment, the user system 140 / 240 may receive digital content 136 / 336 from a content contributor 134 using a transceiver 243. In those embodiments, the digital content 136 / 336 may be received by authenticity analysis software code 210b / 310, which is executed by a hardware processor 244 of the user system 140 / 240 and uses a content reception and recognition module 312.

[0056] Flowchart 570 continues by identifying the image of a person depicted in digital content 136 / 336, where the depiction includes the person's participation in a monologue and / or dialogue depicted in the image (action 572). In some embodiments, digital content 136 / 336 may be AV content that includes images of well-known people, such as celebrity athletes, actors, or politicians. However, more generally, the person depicted in digital content 136 / 336 and identified in action 572 may be anyone with one or more corresponding language profiles (e.g., language profiles 122a / 226a / 326a and / or language profiles 122b / 226b / 326b stored in language database 124 / 224 / 320). For example, such a person may be an actor, journalist, news anchor, or other talent employed by a media entity that includes system 100 / 200 as a QC resource.

[0057] It should be noted that in embodiments where digital content 136 / 336 includes more than one person as a participant but only the authentication of one person's identity is of interest, the audio track included in digital content 136 / 336 may be segmented into different audio signals to isolate each participant, for example, using a voiceprint segmentation clustering algorithm. Once the audio of each person's speech is separated into its own audio file, the actions outlined in flowchart 570 may be performed on the audio data corresponding to the person of interest, but not on others.

[0058] It should also be noted that the same person may have multiple language profiles stored in language database 124 / 224 / 324. For example, as an actor ages, they may have different language profiles at different stages of their career. Alternatively, or in addition, an actor may have different language profiles for each role they play or each movie or other audio performance they participate in. Furthermore, in some embodiments, it may be advantageous or desirable for a person to have multiple language profiles, each focusing on different linguistic habits or attributes. That is, for example, the same actor may have a first language profile for a speech defect they have had, overcome, or depicted over time, a second biometric profile for an accent they have developed over time, and so on.

[0059] In an implementation where the digital content 136 / 336 is received by the system 100 / 200 in operation 571, the identification of the person depicted in the image included in the digital content 136 / 336 can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the content receiving and identification module 312. However, in an implementation where the digital content 136 / 336 is received by the user system 140 / 240 in operation 571, the identification of the person depicted in the image included in the digital content 136 / 336 can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the content receiving and identification module 312.

[0060] Flowchart 570 continues by detecting at least one language habit (operation 573) of the person depicted in the identified image in operation 572, based on the participation in the monologue and / or dialogue. One or more language habits detected in operation 573 can include, among others, one or more of the speech defects, speech mannerisms, speech rhythms, regional accents or regional dialects of the person depicted in the image. In an implementation where the digital content 136 / 336 is received by the system 100 / 200 in operation 571, the detection of one or more language habits of the person depicted in the identified image in operation 572 can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the language comparison module 316. However, in an implementation where the digital content 136 / 336 is received by the user system 140 / 240 in operation 571, the detection of one or more language habits of the person depicted in the identified image in operation 572 can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the language comparison module 316.

[0061] Flowchart 570 continues by obtaining one of the language profiles 126a / 226a / 326a or 126b / 226b / 326b of the person depicted in the image and identified in action 572, where the language profile includes one or more predetermined language habits of the person depicted in the image (action 574). In an implementation where the system 100 / 200 receives the digital content 136 / 336 in action 571, obtaining one of the language profiles 126a / 226a / 326a or 126b / 226b / 326b from the language database 124 / 224 / 324 can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the language comparison module 316.

[0062] However, in an implementation where the user system 140 / 240 receives the digital content 136 / 336 in action 571, obtaining one of the language profiles 126a / 226a / 326a or 126b / 226b / 326b from the language database 124 / 224 / 324 can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the language comparison module 316. For example, in those later implementations, the user system 140 / 240 can utilize the transceiver 243 and the communication network 130 to access the language database 124 / 224 / 324 stored on the computing platform 102 / 202 of the system 100 / 200 to obtain one of the language profiles 126a / 226a / 326a or 126b / 226b / 326b.

[0063] Flowchart 570 continues by comparing one or more of the detected language habits in action 573 with one or more of the predetermined language habits included in one of the language profiles 126a / 226a / 326a or 126b / 226b / 326b (action 575). For example, in cases where the person identified as being depicted in the image is an actor, journalist, news anchor, or other talent employed by a media entity that includes the system 100 / 200 as a QC resource, language profiles including one or more language habits of each such individual can be stored in the language database 124 / 224 / 324, for example, as part of one of the language profiles 126a / 226a / 326a or 126b / 226b / 326b. Action 575 can be performed by using a speech-to-text algorithm to translate the audio and identifying repetitive vocabulary from that person compared to others. A metric that can be used in action 575 is the well-known term frequency - inverse document frequency (TF-IDF).

[0064] In an implementation where the system 100 / 200 receives the digital content 136 / 336 in operation 571, the comparison of one or more detected linguistic habits in operation 573 with one or more predetermined linguistic habits included in one of the language profiles 126a / 226a / 326a or 126b / 226b / 326b can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the language comparison module 330. However, in an implementation where the user system 140 / 240 receives the digital content 136 / 336 in operation 571, the comparison of one or more detected linguistic habits in operation 573 with one or more predetermined linguistic habits included in one of the language profiles 126a / 226a / 326a or 126b / 226b / 326b can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the language comparison module 316. It should be noted that operation 575 causes the linguistic habit comparison 356 to be provided as an input by the language comparison module 316 to the authentication module 318 of the authenticity analysis software code 110 / 210a / 310 or the authenticity analysis software code 210b / 310.

[0065] In an implementation where the person whose identity is authenticated is an actor or other type of performer, it may be advantageous or desirable to distinguish the predetermined linguistic habits of the person "in character" from the predetermined linguistic habits exhibited when they are speaking as their true selves. For example, such a distinction will help to identify deepfake digital content where the performer speaking as their true self exhibits the linguistic habits of a person or character they have played in the past. Such a distinction will also help to identify deepfake digital content where the deepfake generator is trained based on an interview with the performer as their true self, but the deepfake depicts the person as if they were performing a role.

[0066] The exemplary method outlined in flow chart 570 can end with determining whether the person depicted in the image is a true depiction of the person (action 576) based on a comparison 356 of one or more detected linguistic habits in action 573 with one or more predefined linguistic habits included in one of language profiles 126a / 226a / 326a or 126b / 226b / 326b. For example, when the linguistic habit comparison 356 shows a match within a predefined tolerance between one or more detected linguistic habits in action 573 and one or more predefined linguistic habits included in one of language profiles 126a / 226a / 326a or 126b / 226b / 326b, authenticity determination 138 / 238 / 338 identifies the person depicted in the image as a true depiction of the person. Additionally, in some embodiments, action 576 can include determining that digital content 136 / 336 is authentic when, based on a comparison of one or more detected linguistic habits with one or more predefined linguistic habits, the person depicted in the image matches a true depiction of the person.

[0067] In embodiments where the system 100 / 200 receives digital content 136 / 336 in action 571, action 576 can be performed by authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of computing platform 102 / 202 and uses authentication module 318 to output authenticity determination 138 / 238 / 338. However, in embodiments where the user system 140 / 240 receives digital content 136 / 336 in action 571, action 576 can be performed by authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of user system 140 / 240 and uses authentication module 318 to output authenticity determination 138 / 238 / 338.

[0068] It should be noted that in some embodiments, the hardware processor 104 / 204 can execute the authenticity analysis software code 110 / 210a / 310, or the hardware processor 244 of the user system 140 / 240 can execute the authenticity analysis software code 210b / 310 to perform actions 571, 572, 573, 574, 575, and 576 in an automated process that can omit human participation.

[0069] Now in conjunction with Figure 1 、 Figure 2 and Figure 3 and with reference to Figure 6 as described above, Figure 6FIG. 680 is a flow chart representing an exemplary method used by a system for authenticating digital content according to yet another embodiment. Flow chart 680 begins with: receiving digital content 136 / 336 having an audio track that includes a monologue and / or dialogue (action 681). As described above, in some embodiments, digital content 136 / 136 may take the form of audio-only or AV content without video, such as: movies; serialized content including TV show series, web series, and / or video blogs; sports content; news content; advertising content or video game content having an audio track that includes a monologue and / or dialogue, and so on.

[0070] As Figure 1 shown, in one embodiment, system 100 may receive digital content 136 from content contributor 134 or user system 140 via communication network 130 and network communication link 132. In those embodiments, digital content 136 / 336 may be received by authenticity analysis software code 110 / 210a / 310, which is executed by hardware processor 104 / 204 of computing platform 102 / 202 and uses content reception and recognition module 312. However, in Figure 1 connection Figure 2 therewith, in another embodiment, user system 140 / 240 may receive digital content 136 / 336 from content contributor 134 using transceiver 243. In those embodiments, digital content 136 / 336 may be received by authenticity analysis software code 210b / 310, which is executed by hardware processor 244 of user system 140 / 240 and uses content reception and recognition module 312.

[0071] Flow chart 680 continues by identifying digital content 136 / 336 as pre-existing content having a corresponding script stored in language database 124 / 224 / 324 (action 682). In some embodiments, digital content 136 / 336 may be AV content in the form of, for example, previously produced movies, TV shows, news broadcasts, sports broadcasts, interviews, advertisements, or video games. However, more generally, digital content 136 / 336 identified as pre-existing content in action 682 may be any digital content that includes a monologue and / or dialogue, where the corresponding script (e.g., script 127a / 227a / 327a or 127b / 227b / 327b) is stored in language database 124 / 224 / 324.

[0072] In an implementation where the system 100 / 200 receives the digital content 136 / 336 in action 681, identifying the digital content 136 / 336 as pre - existing content having a corresponding script stored in the language database 124 / 224 / 324 can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the content receiving and identifying module 312. However, in an implementation where the user system 140 / 240 receives the digital content 136 / 336 in action 681, identifying the digital content 136 / 336 as pre - existing content having a corresponding script stored in the language database 124 / 224 / 324 can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the content receiving and identifying module 312.

[0073] Flowchart 680 continues by extracting samples of the monologues and / or dialogues included in the digital content 136 / 336 (action 683). Depending on the particular use case, action 683 can include sampling all of the monologues and / or dialogues included in the digital content 136 / 336, or less than all of the monologues and / or dialogues. For example, in a use case where less than all of the monologues and / or dialogues are sampled, a single sample or multiple samples can be extracted from the digital content 136 / 336. When multiple samples are extracted, the samples can be extracted from the digital content 136 / 336 at random intervals, or at predetermined locations or at predetermined intervals, such as time - code locations or time - code intervals, or frame numbers or frame intervals.

[0074] In an implementation where the system 100 / 200 receives the digital content 136 / 336 in action 681, extracting one or more samples of monologues and / or dialogues from the digital content 136 / 336 can be performed by the authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the language comparison module 316. However, in an implementation where the user system 140 / 240 receives the digital content 136 / 336 in action 681, extracting one or more samples of monologues and / or dialogues from the digital content 136 / 336 can be performed by the authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of the user system 140 / 240 and uses the content receiving and identifying module 316.

[0075] Flowchart 680 continues, and a comparison (action 684) is performed on the monologue and / or dialogue samples extracted in action 683 with the corresponding samples from one of scripts 127a / 227a / 327a or 127b / 227b / 327b. For example, in the case where digital content 136 / 336 is content produced or owned by a media entity using system 100 / 200 as a QC resource, all the monologues and / or dialogues and / or closed caption (CC) files included in each item of digital content 136 / 336 produced or owned by the media entity are included in the script, which may be stored in language database 124 / 224 / 324.

[0076] Action 684 can be performed by using a speech-to-text algorithm to translate the audio and comparing the translation with the equivalent part of one of scripts 127a / 227a / 327a or 127b / 227b / 327b. It should be noted that action 684 may include aligning the speech-to-text translation with the script to identify the equivalent part of the script.

[0077] In an implementation where the system 100 / 200 receives digital content 136 / 336 in action 681, the comparison of the monologue and / or dialogue samples extracted in action 683 with the corresponding samples from one of scripts 127a / 227a / 327a or 127b / 227b / 327b can be performed by authenticity analysis software code 110 / 210a / 310; the authenticity analysis software code 110 / 210a / 310 is executed by the hardware processor 104 / 204 of computing platform 102 / 202 and uses language comparison module 316. However, in an implementation where the user system 140 / 240 receives digital content 136 / 336 in action 681, the comparison of the monologue and / or dialogue samples extracted in action 683 with the corresponding samples from one of scripts 127a / 227a / 327a or 127b / 227b / 327b can be performed by authenticity analysis software code 210b / 310; the authenticity analysis software code 210b / 310 is executed by the hardware processor 244 of user system 140 / 240 and uses language comparison module 316. For example, in those later implementations, the user system 140 / 240 can utilize transceiver 243 and communication network 130 to access language database 124 / 224 / 324 stored on the computing platform 102 / 202 of system 100 / 200 to obtain one of scripts 127a / 227a / 327a or 127b / 227b / 327b or a sample thereof. It should be noted that action 684 causes the monologue and / or dialogue comparison 358 to be provided as an input to the authentication module 318 of authenticity analysis software code 110 / 210a / 310 or authenticity analysis software code 210b / 310 by language comparison module 316.

[0078] The exemplary method outlined in flowchart 680 may end by determining whether the monologue and / or dialogue included in the digital content 136 / 336 is authentic based on the monologue and / or dialogue comparison 358 of the sample of the monologue and / or dialogue extracted in act 683 and the corresponding sample of one of the scripts 127a / 227a / 327a or 127b / 227b / 327b (act 685). For example, when the monologue and / or dialogue comparison 358 shows that the match between the sample of the monologue and / or dialogue extracted in act 683 and the corresponding sample of one of the scripts 127a / 227a / 327a or 127b / 227b / 327b is within a predetermined tolerance, the authenticity determination 138 / 238 / 338 identifies the monologue and / or dialogue included in the digital content 136 / 336 as authentic. Additionally, in some embodiments, action 685 may include determining that the digital content 136 / 336 is authentic based on a comparison of the extracted monologue and / or dialogue sample with a corresponding sample of one of the scripts 127a / 227a / 327a or 127b / 227b / 327b, where such corresponding sample may include content of the monologue and / or dialogue and / or CC file.

[0079] In embodiments where the digital content 136 / 336 is received by the system 100 / 200 in act 681, act 685 may be performed by the authenticity analysis software code 110 / 210a / 310 which is executed by the hardware processor 104 / 204 of the computing platform 102 / 202 and uses the authentication module 318 to output the authenticity determination 138 / 238 / 338. However, in embodiments where the digital content 136 / 336 is received by the user system 140 / 240 in act 681, act 685 may be performed by the authenticity analysis software code 210b / 310 which is executed by the hardware processor 244 of the user system 140 / 240 and uses the authentication module 318 to output the authenticity determination 138 / 238 / 338.

[0080] It should be noted that in some embodiments, the hardware processor 104 / 204 can execute the authenticity analysis software code 110 / 210a / 310, or the hardware processor 244 of the user system 140 / 240 can execute the authenticity analysis software code 210b / 310 to perform actions 681, 682, 683, 684, and 685 in an automated process that can omit human involvement. It should also be noted that in the above Figure 4 , Figure 5 and Figure 6The methods in [the above] can be used in combination to authenticate digital content. In other words, in some embodiments, the methods described in flowcharts 460 and 570 can be executed together to determine the authenticity of digital content; and in other embodiments, the methods described in flowcharts 460 and 680 can be executed together as part of the authenticity assessment. In other embodiments, the methods described in flowcharts 570 and 680 can be executed together. In yet another embodiment, the methods described in flowcharts 460, 570, and 680 can be executed together to determine the authenticity of digital content.

[0081] Accordingly, the present application discloses a system for authenticating digital content, which overcomes the disadvantages and deficiencies in the conventional art. From the above description, it is obvious that various techniques can be used to implement these concepts without departing from the scope of the concepts described in the present application. In addition, although these concepts have been specifically described with reference to certain embodiments, those of ordinary skill in the art will recognize that changes in form and detail can be made without departing from the scope of these concepts. Therefore, the described embodiments are considered illustrative rather than restrictive in all respects. It should also be understood that the present application is not limited to the specific embodiments described herein, but many rearrangements, modifications, and substitutions can be made without departing from the scope of the present disclosure.

Claims

1. A system for authenticating digital content, the system comprising: a computing platform including a hardware processor and a system memory; software code stored in the system memory; the hardware processor being configured to execute the software code to: receive digital content; identify the person depicted in the image in the digital content to determine the identity of the person; determine the ear shape parameters of the person depicted in the image; determine the biometric parameters of the person depicted in the image, the biometric parameters being different from the ear shape parameters; calculate the ratio of the ear shape parameters of the person depicted in the image to the biometric parameters of the person depicted in the image; use the determined identity to obtain from a database a predetermined value of the ratio of the ear shape parameters to the biometric parameters of the identified person, wherein the predetermined value is associated with the identified person in the database; compare the ratio calculated for the person depicted in the image with the predetermined value of the identified person obtained from the database; and based on the comparison of the ratio calculated for the person depicted in the image with the predetermined value associated with the identified person in the database, determine whether the person depicted in the image is a true depiction of the identified person.

2. The system according to claim 1, wherein the hardware processor is further configured to execute software code to: when it is determined, based on the comparison of the calculated ratio with the predetermined value, that the person depicted in the image is a true depiction of the person, determine that the digital content is authentic.

3. The system according to claim 1, wherein the biometric parameters of the person depicted in the image include: the distance between the two eyes of the person depicted in the image.

4. The system according to claim 1, wherein the biometric parameters of the person depicted in the image include at least one of: the eye shape parameters or the mouth shape parameters of the person depicted in the image.

5. The system according to claim 1, wherein the digital content includes at least one of: sports content, television program content, movie content, advertising content, or video game content.

6. The system according to claim 1, wherein the computing platform includes at least one web-based computer server.

7. The system according to claim 1, wherein the computing platform includes a mobile communication device.

8. The system according to claim 1, wherein the ear shape parameters of the person depicted in the image include a single dimension of the ear of the person depicted in the image.

9. The system according to claim 1, wherein the ear shape parameters of the person depicted in the image include a combination of multiple ear dimensions of the person depicted in the image.

10. The system according to claim 1, wherein the biometric parameters of the person depicted in the image include a combination of multiple facial parameters of the person depicted in the image.

11. A method for authenticating digital content, the method comprising: receiving digital content; identifying the person depicted in the image in the digital content to determine the identity of the person; determining the ear shape parameters of the person depicted in the image; determining the biometric parameters of the person depicted in the image, the biometric parameters being different from the ear shape parameters; calculating the ratio of the ear shape parameters of the person depicted in the image to the biometric parameters of the person depicted in the image; Using the determined identity, obtain the ear shape parameters of the identified person from the database to compare with the predetermined values of the biometric parameters, where the predetermined values are associated with the identified person in the database; Compare the ratio calculated for the person depicted in the image with the predetermined values of the identified person obtained from the database; And Based on the comparison of the ratio calculated for the person depicted in the image with the predetermined values associated with the identified person in the database, determine whether the person depicted in the image is a true depiction of the identified person.

12. The method according to claim 11, further comprising: When it is determined, based on the comparison of the calculated ratio with the predetermined value, that the person depicted in the image is a true depiction of the person, determine that the digital content is authentic.

13. The method according to claim 11, wherein, The biometric parameters of the person depicted in the image include: the distance between the two eyes of the person depicted in the image.

14. The method according to claim 11, wherein, The biometric parameters of the person depicted in the image include at least one of the eye shape parameters or mouth shape parameters of the person depicted in the image.

15. The method according to claim 11, wherein, The digital content includes at least one of sports content, TV program content, movie content, advertising content, or video game content.

16. The method according to claim 11, wherein, The method is executed by at least one web-based computer server.

17. The method according to claim 11, wherein, The method is executed by a mobile communication device.

18. The method according to claim 11, wherein, The ear shape parameters of the person depicted in the image include a single dimension of the ear of the person depicted in the image.

19. The method according to claim 11, wherein, The ear shape parameters of the person depicted in the image include a combination of multiple ear dimensions of the person depicted in the image.

20. The method according to claim 11, wherein, The biometric parameters of the person depicted in the image include a combination of multiple facial parameters of the person depicted in the image.

Images