Method for detecting fake content by utilizing angle of person in video

Abstract

A method by which one or more processors of a computing device detect fake content, according to one embodiment of the present disclosure, is disclosed. The method may comprise the steps of: acquiring a reference image and a target video including a person; acquiring a first frame image included in the target video and a second frame image that differs from the first frame image; calculating a first similarity between the reference image and the first frame image, and calculating a second similarity between the reference image and the second frame image; and predicting whether the target video is fake content on the basis of the calculated first similarity and second similarity.

Description

A method for detecting fake content by utilizing the angle of the person in the video.

[0001] The present disclosure relates to a method for detecting false content, and more particularly, to a method for detecting false content by utilizing the facial angle of a person included in a video.

[0002] With recent technological advancements, deepfake technology, or face-swapping, a face-transforming technique, is being utilized in various fields such as film and image synthesis. While deepfake technology has been effective in reducing the burden on filmmakers and reducing the time and cost required for filming, it has also raised concerns that forged video content can undermine the credibility of news and information, making it difficult for consumers to discern trustworthy information. Furthermore, fake content videos created using deepfake technology can be used to threaten or deceive individuals or organizations, and can even be distributed with malicious intent against specific individuals or groups. Therefore, the need for methods to detect fake content is emerging to address these issues.

[0003] Meanwhile, while the present disclosure was derived at least based on the technical background discussed above, the technical task or purpose of the present disclosure is not limited to resolving the problems or shortcomings discussed above. That is, in addition to the technical issues discussed above, the present disclosure can cover various technical issues related to the content described below.

[0004] The present disclosure relates to a method for detecting false content, and more specifically, to a problem of detecting false content more accurately by utilizing the facial angle of a person included in a video.

[0005] Meanwhile, the technical task to be achieved by the present disclosure is not limited to the technical task mentioned above, and may include various technical tasks within a scope obvious to a person skilled in the art from the contents described below.

[0006] According to one embodiment of the present disclosure for achieving the above-described task, a method performed by a computing device is disclosed. The method may include the steps of: obtaining a target video including a reference image and a person; obtaining a first frame image included in the target video and a second frame image different from the first frame image; calculating a first similarity between the reference image and the first frame image and calculating a second similarity between the reference image and the second frame image; and predicting whether the target video contains false content based on the calculated first similarity and the second similarity.

[0007] Alternatively, the step of obtaining a first frame image included in the target video and a second frame image different from the first frame image may include the step of obtaining a first frame image included in the target video and a second frame image including a face of a person included in the first frame image at a different angle.

[0008] Alternatively, the step of obtaining a first frame image included in the target video and a second frame image including a face of a person included in the first frame image at different angles may include the step of obtaining a first frame image including a face of a person at an angle within a preset threshold with respect to the front; and the step of obtaining a second frame image including a face of a person at an angle exceeding the preset threshold with respect to the front.

[0009] Alternatively, the step of obtaining a first frame image included in the target video and a second frame image different from the first frame image may further include a step of performing super resolution processing on at least one of the obtained first frame image or the second frame image.

[0010] Alternatively, the step of calculating a first similarity between the reference image and the first frame image and calculating a second similarity between the reference image and the second frame image may include the steps of: performing encoding on the reference image using a neural network model and obtaining a reference encoding vector; performing encoding on the first frame image using the neural network model to obtain a first encoding vector and performing encoding on the second frame image to obtain a second encoding vector; and calculating a first similarity between the reference encoding vector and the first encoding vector and calculating a second similarity between the reference encoding vector and the second encoding vector.

[0011] Alternatively, the neural network model may include a pre-trained model to extract identity features for facial images of a person.

[0012] Alternatively, the reference image may include an image obtained from a reference video containing a specific person.

[0013] Alternatively, the reference image may include a first reference image included in the reference video and a second reference image included in the reference video that is different from the first reference image, and the step of calculating a first similarity between the reference image and the first frame image and calculating a second similarity between the reference image and the second frame image may include the step of calculating a first similarity between the first reference image and the first frame image and calculating a second similarity between the second reference image and the second frame image.

[0014] Alternatively, the step of calculating a first similarity between the reference image and the first frame image and calculating a second similarity between the reference image and the second frame image may include the step of calculating a reference similarity between the first reference image and the second reference image and calculating a second similarity between the first reference image and the second frame image.

[0015] Alternatively, the step of predicting whether the target video is a false content based on the calculated first similarity and the second similarity may include the step of calculating a difference between the calculated first similarity and the second similarity; and the step of predicting whether the target video is a false content based on the difference in the calculated similarity.

[0016] Alternatively, the step of predicting whether the target video is false content based on the difference in the calculated similarity may include the step of predicting the target video as false content if the second similarity decreases compared to the calculated first similarity.

[0017] Alternatively, the step of predicting whether the target video is false content based on the difference in the calculated similarity may include a step of predicting the target video as false content if the difference in the calculated similarity is greater than a preset threshold.

[0018] According to one embodiment of the present disclosure for achieving the above-described task, a computer program stored in a computer-readable storage medium is disclosed. When the computer program is executed on one or more processors, the one or more processors may perform operations for detecting false content, the operations including: obtaining a target video including a reference image and a person; obtaining a first frame image included in the target video and a second frame image different from the first frame image; calculating a first similarity between the reference image and the first frame image and calculating a second similarity between the reference image and the second frame image; and predicting whether the target video contains false content based on the calculated first similarity and the second similarity.

[0019] Alternatively, the operation of obtaining a first frame image included in the target video and a second frame image different from the first frame image may include the operation of obtaining a first frame image included in the target video and a second frame image including a face of a person included in the first frame image at a different angle.

[0020] Alternatively, the operation of obtaining a first frame image included in the target video and a second frame image including a face of a person included in the first frame image at different angles may include an operation of obtaining a first frame image including a face of a person at an angle within a preset threshold with respect to the front; and an operation of obtaining a second frame image including a face of a person at an angle exceeding a preset threshold with respect to the front.

[0021] Alternatively, the operation of obtaining a first frame image included in the target video and a second frame image different from the first frame image may further include an operation of performing super resolution processing on at least one of the obtained first frame image or the second frame image.

[0022] Alternatively, the operation of calculating a first similarity between the reference image and the first frame image and calculating a second similarity between the reference image and the second frame image may include: performing encoding on the reference image using a neural network model and obtaining a reference encoding vector; performing encoding on the first frame image using the neural network model to obtain a first encoding vector and performing encoding on the second frame image to obtain a second encoding vector; and calculating a first similarity between the reference encoding vector and the first encoding vector and calculating a second similarity between the reference encoding vector and the second encoding vector.

[0023] Alternatively, the operation of calculating a first similarity between the reference image and the first frame image and calculating a second similarity between the reference image and the second frame image may include the operation of calculating a first similarity between the first reference image and the first frame image and calculating a second similarity between the second reference image and the second frame image.

[0024] Alternatively, the operation of predicting whether the target video is a false content based on the calculated first similarity and the second similarity may include the operation of calculating a difference between the calculated first similarity and the second similarity; and the operation of predicting whether the target video is a false content based on the difference in the calculated similarity.

[0025] Alternatively, the operation of predicting whether the target video is false content based on the difference in the calculated similarity may include an operation of predicting the target video as false content if the second similarity decreases compared to the calculated first similarity.

[0026] Alternatively, the operation of predicting whether the target video is false content based on the difference in the calculated similarity may include an operation of predicting the target video as false content if the difference in the calculated similarity is greater than a preset threshold.

[0027] A computing device according to one embodiment of the present disclosure for achieving the above-described task is disclosed. The device may be configured to acquire a target video including a reference image and a person; acquire a first frame image included in the target video and a second frame image different from the first frame image; calculate a first similarity between the reference image and the first frame image, and calculate a second similarity between the reference image and the second frame image; and predict whether the target video contains false content based on the calculated first similarity and the second similarity.

[0028] In order to achieve the above-described task, a data structure included in a computer-readable storage medium according to one embodiment of the present disclosure is disclosed. The data structure corresponds to parameters of a neural network, and the neural network performs the following steps at least partially based on the parameters, wherein the steps may include: obtaining a target video including a reference image and a person; obtaining a first frame image included in the target video and a second frame image different from the first frame image; calculating a first similarity between the reference image and the first frame image and calculating a second similarity between the reference image and the second frame image; and predicting whether the target video contains false content based on the calculated first similarity and the second similarity.

[0029] The present disclosure relates to a method for detecting false content, and more specifically, to detect false content more accurately by utilizing the facial angle of a person included in a video.

[0030] Meanwhile, the effects of the present disclosure are not limited to the effects mentioned above, and various effects may be included within a range apparent to those skilled in the art from the contents described below.

[0031] FIG. 1 is a block diagram of a computing device for detecting false content by utilizing the angle of a video character according to one embodiment of the present disclosure.

[0032] FIG. 2 is a schematic diagram illustrating a network function according to one embodiment of the present disclosure.

[0033] FIG. 3 is a flowchart illustrating a method for detecting false content by utilizing the angle of a video character according to one embodiment of the present disclosure.

[0034] FIG. 4 is a schematic diagram illustrating a process of calculating a first similarity and a second similarity according to one embodiment of the present disclosure and predicting whether the target video is false content based on the same.

[0035] FIG. 5 is a schematic diagram illustrating a process of calculating a first similarity and a second similarity based on a reference video according to one embodiment of the present disclosure and predicting whether the target video is false content based on the same.

[0036] FIG. 6 is a schematic diagram illustrating a process of calculating a reference similarity between a first reference image and a second reference image, calculating a second similarity between the first reference image and a second frame image, and predicting whether the target video contains false content based on the similarity.

[0037] FIG. 7 is a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0038] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to facilitate understanding of the present disclosure. However, it will be apparent that these embodiments may be practiced without these specific details.

[0039] As used herein, the terms "component," "module," "system," and the like refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or an execution of software. For example, a component may be, but is not limited to, a procedure running on a processor, a processor, an object, a thread of execution, a program, and / or a computer. For example, both an application running on a computing device and the computing device may be a component. One or more components may reside within a processor and / or a thread of execution. A component may be localized within a single computer. A component may be distributed between two or more computers. Furthermore, these components may execute from various computer-readable media having various data structures stored therein. Components may communicate via local and / or remote processes, for example, by signals comprising one or more data packets (e.g., data from one component interacting with another component in a local system, a distributed system, and / or data transmitted to another system via a network such as the Internet via signals).

[0040] Furthermore, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from context, "X employs A or B" is intended to mean either of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, "X employs A or B" can apply to any of these cases. Furthermore, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the associated items listed.

[0041] Additionally, the terms "comprises" and / or "comprising" should be understood to imply the presence of the features and / or components in question. However, it should be understood that the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other features, components, and / or groups thereof. Furthermore, unless otherwise specified or clear from the context to refer to the singular form, the singular in the specification and claims should generally be construed to mean "one or more."

[0042] And, the term "at least one of A or B" should be interpreted to mean "if it includes only A", "if it includes only B", or "if it is combined in the composition of A and B".

[0043] Those skilled in the art should further appreciate that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0044] The description of the disclosed embodiments is provided to enable a person skilled in the art to make or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Therefore, the present invention is not limited to the embodiments disclosed herein. The present invention is to be construed in the widest scope consistent with the principles and novel features disclosed herein.

[0045] In the present disclosure, network function and artificial neural network and neural network can be used interchangeably.

[0046]

[0047] FIG. 1 is a block diagram of a computing device for detecting false content by utilizing the angle of a video character according to one embodiment of the present disclosure.

[0048] The configuration of the computing device (100) illustrated in FIG. 1 is merely a simplified example. In one embodiment of the present disclosure, the computing device (100) may include other configurations for performing the computing environment of the computing device (100), and only some of the disclosed configurations may constitute the computing device (100).

[0049] A computing device (100) may include a processor (110), memory (130), and network unit (150).

[0050] The processor (110) may be configured with one or more cores, and may include a processor for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. The processor (110) may read a computer program stored in the memory (130) and perform data processing for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor (110) may perform operations for learning a neural network model. The processor (110) may perform calculations for learning a neural network model, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating weights of a neural network model using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (110) may process learning of the neural network model. For example, a CPU and a GPGPU can work together to train a neural network model and classify data using the neural network model. Furthermore, in one embodiment of the present disclosure, processors of multiple computing devices can be used together to train a neural network model and classify data using the neural network model. Furthermore, a computer program executed on a computing device according to one embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

[0051] According to one embodiment of the present disclosure, the memory (130) can store any form of information generated or determined by the processor (110) and any form of information received by the network unit (150).

[0052] According to one embodiment of the present disclosure, the memory (130) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. The computing device (100) may also operate in relation to web storage that performs the storage function of the memory (130) on the internet. The description of the above-described memory is merely an example, and the present disclosure is not limited thereto.

[0053] The network unit (150) according to one embodiment of the present disclosure can use various wired communication systems such as a public switched telephone network (PSTN), xDSL (x Digital Subscriber Line), RADSL (Rate Adaptive DSL), MDSL (Multi Rate DSL), VDSL (Very High Speed ​​DSL), UADSL (Universal Asymmetric DSL), HDSL (High Bit Rate DSL), and a local area network (LAN).

[0054] In addition, the network unit (150) presented in the present disclosure can use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA) and other systems.

[0055] In the present disclosure, the network unit (150) may be configured regardless of the communication mode, such as wired or wireless, and may be configured as various communication networks, such as a personal area network (PAN) and a wide area network (WAN). In addition, the network may be the well-known World Wide Web (WWW), and may also utilize a wireless transmission technology used for short-distance communication, such as infrared (IrDA: Infrared Data Association) or Bluetooth. The technologies described in the present disclosure may also be used in other networks mentioned above.

[0056]

[0057] FIG. 2 is a schematic diagram illustrating a network function according to one embodiment of the present disclosure.

[0058] Throughout this specification, the terms computational model, neural network, network function, and neural network may be used interchangeably. A neural network may be comprised of a set of interconnected computational units, generally referred to as nodes. These nodes may also be referred to as neurons. A neural network comprises at least one node. The nodes (or neurons) comprising a neural network may be interconnected by one or more links.

[0059] Within a neural network, one or more nodes connected via links can form a relationship between input nodes and output nodes. The concept of input nodes and output nodes is relative, meaning that any node that is in an output node relationship with one node can also be in an input node relationship with another node, and vice versa. As described above, the relationship between input nodes and output nodes can be created based on links. One input node can be connected to one or more output nodes via links, and vice versa.

[0060] In a relationship between input nodes and output nodes connected through a single link, the data of the output node can have its value determined based on the data input to the input node. Here, the link interconnecting the input nodes and output nodes can have a weight. The weight can be variable and can be varied by the user or an algorithm so that the neural network can perform a desired function. For example, when one or more input nodes are interconnected to one output node through each link, the output node can determine the output node value based on the values ​​input to the input nodes connected to the output node and the weight set on the link corresponding to each input node.

[0061] As described above, a neural network is a network in which one or more nodes are interconnected through one or more links, forming input and output node relationships within the network. The characteristics of a neural network can be determined based on the number of nodes and links within the network, the relationships between the nodes and links, and the weights assigned to each link. For example, if two neural networks have the same number of nodes and links but different weight values ​​for the links, the two neural networks can be perceived as different from each other.

[0062] A neural network can be composed of a set of one or more nodes. A subset of the nodes comprising the neural network can form a layer. Some of the nodes comprising the neural network can form a layer based on their distances from the initial input node. For example, a set of nodes that are n distances from the initial input node can form n layers. The distance from the initial input node can be defined by the minimum number of links required to reach the node from the initial input node. However, this definition of a layer is arbitrary for illustrative purposes, and the degree of a layer within a neural network can be defined in a different way than described above. For example, a layer of nodes can be defined by its distance from the final output node.

[0063] An initial input node may refer to one or more nodes within a neural network into which data is directly input without going through links with other nodes. Alternatively, within a neural network, it may refer to nodes that do not have other input nodes connected by links in the relationship between nodes based on links. Similarly, a final output node may refer to one or more nodes within a neural network that do not have output nodes in their relationship with other nodes. Furthermore, a hidden node may refer to nodes that constitute a neural network other than the initial input node and the final output node.

[0064] A neural network according to one embodiment of the present disclosure may be a neural network in which the number of nodes in an input layer may be the same as the number of nodes in an output layer, and the number of nodes decreases and then increases as it progresses from the input layer to the hidden layer. In addition, a neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in an input layer may be less than the number of nodes in an output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. In addition, a neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in an input layer may be greater than the number of nodes in an output layer, and the number of nodes increases as it progresses from the input layer to the hidden layer. A neural network according to another embodiment of the present disclosure may be a neural network in a combined form of the neural networks described above.

[0065] A deep neural network (DNN) can refer to a neural network that includes multiple hidden layers in addition to input and output layers. Using DNNs, one can identify latent structures in data. For example, one can identify the latent structures of images, text, videos, audio, and music (e.g., what objects are in the image, what the content and emotion of the text are, what the content and emotion of the audio are, etc.). DNNs can include convolutional neural networks (CNNs), recurrent neural networks (RNNs), autoencoders, generative adversarial networks (GANs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), Q networks, U networks, Siamese networks, and generative adversarial networks (GANs). The description of the deep neural network described above is only an example and the present disclosure is not limited thereto.

[0066] In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network that outputs output data similar to input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be arranged between input and output layers. The number of nodes in each layer may be reduced from the number of nodes in the input layer to an intermediate layer called a bottleneck layer (encoding), and then expanded symmetrically from the bottleneck layer to the output layer (symmetrical to the input layer). The autoencoder may perform nonlinear dimensionality reduction. The number of input layers and output layers may correspond to the dimensionality after preprocessing of the input data. In the autoencoder structure, the number of nodes in the hidden layer included in the encoder may have a structure in which the number of nodes decreases as it moves away from the input layer. The number of nodes in the bottleneck layer (the layer with the fewest nodes between the encoder and decoder) may be kept above a certain number (e.g., more than half of the input layer), as too few nodes may not transmit enough information.

[0067] Neural networks can learn using at least one of the following methods: supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Neural network learning can be the process of applying knowledge to the neural network to perform a specific action.

[0068] Neural networks can be trained to minimize output errors. This process involves repeatedly inputting training data into the neural network, calculating the neural network output and target error for the training data, and backpropagating the neural network error from the output layer to the input layer to update the weights of each node in the neural network to reduce the error. Supervised learning uses training data with the correct answer labeled for each training data (i.e., labeled training data). Unsupervised learning, on the other hand, may not have the correct answer labeled for each training data. For example, in the case of supervised learning for data classification, the training data may be data with each category labeled. Labeled training data is input to the neural network, and the error can be calculated by comparing the output (category) of the neural network with the training data labels. Alternatively, in the case of unsupervised learning for data classification, the error can be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the neural network in the backward direction (i.e., from the output layer to the input layer), and the connection weights of each node in each layer of the neural network can be updated according to the backpropagation. The amount of change in the connection weights of each node to be updated can be determined by the learning rate. The neural network's calculation of the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle. For example, a high learning rate can be used in the early stages of neural network training to quickly achieve a certain level of performance, thereby increasing efficiency. A lower learning rate can be used in the later stages of training to increase accuracy.

[0069] In neural network training, training data can typically be a subset of real-world data (i.e., the data to be processed using the trained neural network). Therefore, there can be a learning cycle where errors on the training data decrease but errors on the real-world data increase. Overfitting is a phenomenon where excessive training on the training data leads to increased errors on the real-world data. For example, a neural network trained on yellow cats may fail to recognize cats when shown non-yellow colors, a type of overfitting. Overfitting can increase errors in machine learning algorithms. Various optimization methods can be used to prevent overfitting. These methods include increasing the training data, regularization, dropout, which disables some nodes in the network during the learning process, and the use of batch normalization layers.

[0070]

[0071] FIG. 3 is a flowchart illustrating a method for detecting false content by utilizing the angle of a video character according to one embodiment of the present disclosure.

[0072] A computing device (100) according to one embodiment of the present disclosure may directly acquire "information for detecting false content using the angle of a video subject" or receive it from an external system. The external system may be a server, database, or the like that stores and manages information for detecting false content using the angle of a video subject. The computing device (100) may use the information acquired directly or received from the external system as "input data for detecting false content using the angle of a video subject."

[0073] According to one embodiment of the present disclosure, a computing device (100) may acquire a reference image and a target video including a person (S110). At this time, the reference image may include an image that serves as a reference for detecting false content, and the target video including the person may include a video that is to be detected as false content. For example, if the reference image is an image including the face of a specific person A, the target video may include a video that includes the specific person A but is to be detected as false content. Alternatively, the reference image may include an image acquired from a reference video including a specific person. For example, the reference video may include a video including the face of a specific person A, and the reference video may include a first reference image and a second reference image. Meanwhile, the acquired reference image and target video may be utilized in a process in which the computing device (100) predicts whether the target video is false content, which will be described later with reference to FIGS. 4 and 5 .

[0074] According to one embodiment of the present disclosure, the computing device (100) can acquire a first frame image included in the target video acquired through step S110 and a second frame image different from the first frame image (S120). Specifically, the computing device (100) can acquire the first frame image included in the target video and a second frame image including a face of a person included in the first frame image at a different angle. For example, the computing device (100) can acquire a first frame image including a face of a person at an angle within a preset threshold with respect to the front, and can acquire a second frame image including a face of a person at an angle exceeding the preset threshold with respect to the front. Meanwhile, the computing device (100) can perform super-resolution processing on at least one of the acquired first frame image or the second frame image in the process of acquiring the first frame image included in the target video and the second frame image different from the first frame image. In this regard, in the case of fake content videos, there are many cases where the quality is low enough to make it difficult to determine whether it is genuine, and in general, in cases of low quality, the boundary of face transformation is blurred, making it even more difficult to determine whether it is genuine. Therefore, the computing device (100) can increase the accuracy of determining whether the fake content video is genuine by performing super-resolution processing on at least one of the first frame image or the second frame image obtained in the process of obtaining the first frame image included in the target video and the second frame image different from the first frame image.At this time, in the process of the computing device (100) performing the super resolution processing, technologies such as SRCNN (Super-Resolution Convolutional Neural Network), ESPCN (Efficient Sub-Pixel Convolutional Neural Network), SRGAN (Super-Resolution Generative Adversarial Network), and DRCN (Deep Recursive Convolutional Network) may be utilized, but are not limited thereto.

[0075] Thereafter, according to one embodiment of the present disclosure, the computing device (100) may calculate a first similarity between the reference image acquired through step S110 and the first frame image acquired through step S120, and may calculate a second similarity between the reference image and the second frame image acquired through step S120 (S130). For example, the computing device (100) may perform encoding on the reference image using a neural network model and obtain a reference encoding vector, may perform encoding on the first frame image using the neural network model to obtain a first encoding vector, and may perform encoding on the second frame image to obtain a second encoding vector. In addition, the computing device (100) may calculate a first similarity between the reference encoding vector and the first encoding vector, and may calculate a second similarity between the reference encoding vector and the second encoding vector. At this time, the neural network model may include a pre-trained model to extract identity features for a person's face image, and examples thereof may utilize technologies such as FaceNet, OpenFace, DeepFace, ArcFace, and VGGFace, but are not limited thereto. In addition, in the process of calculating the similarity between the reference encoding vector and the first or second encoding vector, cosine similarity, etc. may be calculated, but the present invention is not limited thereto, and various examples available to a person skilled in the art may be utilized for similarity calculation. In this regard, a person included in the first or second frame image and a person included in the reference image may have similar facial features, but may have differences in hair style, hair color, background, lighting, etc.In this case, when the computing device (100) calculates the similarity between the reference image and the first or second frame image in units of pixels, other secondary features may be reflected in addition to the facial features, thereby reducing the accuracy of the calculation. Therefore, the computing device (100) performs encoding on the reference image, the first and second frame images, calculates a first similarity between the reference encoding vector and the first encoding vector, and calculates a second similarity between the reference encoding vector and the second encoding vector, thereby reducing the influence of other secondary features other than the facial features in the similarity calculation process and increasing the accuracy of the similarity calculation.

[0076] According to one embodiment of the present disclosure, the computing device (100) may calculate a first similarity between the first reference image and the first frame image, and a second similarity between the second reference image and the second frame image. For example, the computing device (100) may calculate a first similarity between “the first reference image and the first frame image, in which a person included in the image is looking straight ahead,” and may calculate a second similarity between “the second reference image and the second frame image, in which a person included in the image is looking sideways.” Through this, the computing device (100) may calculate a similarity by comparing the front and front and the side of the first and second reference images and the first and second frame images, thereby compensating for an error due to an angle difference between the objects of similarity calculation and increasing the accuracy of the similarity calculation.

[0077] According to one embodiment of the present disclosure, the computing device (100) may calculate a reference similarity between the first reference image and the second reference image, and may calculate a second similarity between the first reference image and the second frame image. In this regard, since the first reference image and the second reference image are images included in a reference video for a specific person A, the calculated similarity between the first reference image and the second reference image may be calculated as a reference similarity that takes into account differences according to angles of the same person looking at the front and the side. On the other hand, since the second frame image is an image included in a target video that is a target of determining whether or not a false content is authentic, the calculated second similarity between the first reference image and the second frame image may be used in a process in which the computing device (100) determines whether or not a false content is authentic by comparing it with the calculated reference similarity.

[0078] According to one embodiment of the present disclosure, the computing device (100) can predict whether the target video is a false content based on the first similarity and the second similarity calculated through step S130 (S140). Specifically, the computing device (100) can calculate the difference between the calculated first similarity and the second similarity, and predict whether the target video is a false content based on the difference in the calculated similarity. For example, the computing device (100) can predict the target video as a false content if the second similarity decreases compared to the calculated first similarity. As another example, the computing device (100) can predict the target video as a false content if the difference in the calculated similarity is greater than or equal to a preset threshold. In this regard, in the case of a technology for changing faces, such as face swap, since the face is changed using an image close to the front, the greater the difference in the face shape or angle between the person whose face is being changed and the person, the lower the quality of the changed face, and the lower the naturalness of the changed face. On the other hand, in the case of an original video (i.e., a reference video) that is not a fake content, the problem of the naturalness of the face expressed in the video being reduced due to the difference in angle does not occur because the face has not been changed. Therefore, the computing device (100) according to an embodiment of the present disclosure can detect the fake content more accurately by using the face angle of the person included in the video by predicting the target video as a fake content when the similarity between the person included in the reference image and the target video is calculated differently depending on the angle. Meanwhile, in the process in which the computing device (100) detects the fake content more accurately by using the face angle of the person included in the video, various examples based on the similarity between the reference image and the first and second frame images can be used, and a description thereof will be described later with reference to FIGS. 5 and 6.

[0079]

[0080] FIG. 4 is a schematic diagram illustrating a process of calculating a first similarity and a second similarity according to one embodiment of the present disclosure and predicting whether the target video is false content based on the same.

[0081] Referring to FIG. 4, the computing device (100) can obtain a reference image (20) and target videos (10-1 to 10-4) including a person. At this time, the reference image (20) may include an image that serves as a reference for detecting false content, and the target videos (10-1 to 10-4) including the person may include a video that is a target for detection as to whether it is false content. For example, if the reference image (20) is an image that includes the face of a specific person A, the target videos (10-1 to 10-4) may include a video that includes the specific person A but is a target for detection as to whether it is false content.

[0082] In addition, the computing device (100) can obtain a first frame image (10-1) included in the target video (10-1 to 10-4) and a second frame image (10-3) different from the first frame image (10-1). Specifically, the computing device (100) can obtain a first frame image (10-1) included in the target video (10-1 to 10-4) and a second frame image (10-3) including a face of a person included in the first frame image at a different angle. For example, the computing device (100) can obtain a first frame image (10-1) including a face of a person at an angle within a preset threshold of 30 degrees with respect to the front, and can obtain a second frame image (10-3) including a face of a person at an angle exceeding a preset threshold of 30 degrees with respect to the front. Meanwhile, the computing device (100) may perform super-resolution processing on at least one of the first frame image (10-1) included in the target video and the second frame image (10-3) different from the first frame image in the process of obtaining the first frame image or the second frame image. In this regard, in the case of fake content videos, there are many cases where the quality is low enough to make it difficult to determine whether it is genuine, and in general, in the case of low quality, the boundary of face transformation is blurred, so it may become more difficult to determine whether the fake content is genuine. Accordingly, the computing device (100) can increase the accuracy of determining the authenticity of a fake content video by performing super resolution processing on at least one of the acquired first frame image (10-1) or second frame image (10-3) in the process of acquiring the first frame image (10-1) included in the target video (10-1 to 10-4) and the second frame image (10-3) different from the first frame image.At this time, in the process of the computing device (100) performing the super resolution processing, technologies such as SRCNN (Super-Resolution Convolutional Neural Network), ESPCN (Efficient Sub-Pixel Convolutional Neural Network), SRGAN (Super-Resolution Generative Adversarial Network), and DRCN (Deep Recursive Convolutional Network) may be utilized, but are not limited thereto.

[0083] Thereafter, the computing device (100) can calculate the first similarity between the reference image (20) and the first frame image (10-1) as 0.9, and can calculate the second similarity between the reference image (20) and the second frame image (10-3) as 0.7. For example, the computing device (100) can perform encoding on the reference image (20) using a neural network model and obtain a reference encoding vector, can perform encoding on the first frame image (10-1) using the neural network model to obtain a first encoding vector, and can perform encoding on the second frame image (10-3) to obtain a second encoding vector. In addition, the computing device (100) can calculate the first similarity between the reference encoding vector and the first encoding vector, and can calculate the second similarity between the reference encoding vector and the second encoding vector. At this time, the neural network model may include a pre-trained model to extract identity features for a person's face image, and examples thereof may utilize technologies such as FaceNet, OpenFace, DeepFace, ArcFace, and VGGFace, but are not limited thereto. In addition, in the process of calculating the similarity between the reference encoding vector and the first or second encoding vector, cosine similarity, etc. may be calculated, but the present invention is not limited thereto, and various examples available to a person skilled in the art may be utilized for similarity calculation. In this regard, the person included in the first or second frame image (10-1 or 10-3) and the person included in the reference image (20) may have similar facial features, but may have differences in hair style, hair color, background, lighting, etc.In this case, when the computing device (100) calculates the similarity between the reference image (20) and the first or second frame image (10-1 or 10-3) in units of pixels, other secondary features may be reflected in addition to the facial features, thereby reducing the accuracy of the calculation. Therefore, the computing device (100) performs encoding on the reference image (20) and the first and second frame images (10-1 and 10-3), calculates the first similarity between the reference encoding vector and the first encoding vector, and calculates the second similarity between the reference encoding vector and the second encoding vector, thereby reducing the influence of other secondary features other than the facial features in the similarity calculation process and increasing the accuracy of the similarity calculation.

[0084] In addition, the computing device (100) can calculate the difference between the calculated first similarity (0.9) and the second similarity (0.7), and predict whether the target videos (10-1 to 10-4) are false content based on the difference in the calculated similarities. For example, the computing device (100) can predict the target videos (10-1 to 10-4) as false content if the second similarity decreases to 0.7 compared to the calculated first similarity of 0.9. As another example, the computing device (100) can predict the target videos (10-1 to 10-4) as false content if the difference in the calculated similarities is greater than or equal to a preset threshold of 0.2. However, the preset threshold is not limited to the above example, and various other examples may be utilized. In this regard, in the case of a technology for changing faces, such as face swap, since the face change is performed by utilizing an image close to the front, the greater the difference in the face shape or angle between the person whose face is being changed and the person, the lower the quality of the changed face, and the lower the naturalness of the changed face. On the other hand, in the case of an original video (i.e., a reference video) that is not a fake content, the problem of the naturalness of the face expressed in the video deteriorating depending on the difference in angle does not occur because the face change was not performed. Therefore, the computing device (100) according to one embodiment of the present disclosure can detect the fake content more accurately by utilizing the face angle of the person included in the video by predicting the target video (10-1 to 10-4) as a fake content when the similarity between the person included in the reference image and the target video is calculated differently depending on the angle.Meanwhile, in the process of the computing device (100) detecting false content more accurately by utilizing the face angle of a person included in the video, various examples based on the similarity between the reference image and the first and second frame images can be utilized, and the descriptions thereof will be described later with reference to FIGS. 5 and 6.

[0085]

[0086] FIG. 5 is a schematic diagram illustrating a process of calculating a first similarity and a second similarity based on a reference video according to one embodiment of the present disclosure and predicting whether the target video is false content based on the same.

[0087] Referring to FIG. 5, the computing device (100) can acquire an image included in a reference video (20-1 to 20-4) including a specific person as the reference image. For example, the reference video (20-1 to 20-4) may include a video including the face of a specific person A, and the reference video (20-1 to 20-4) may include a first reference image (20-1) and a second reference image (20-3). At this time, the first reference image (20-1) and the second reference image (20-3) may include frames in different time series. For example, if the first reference image (20-1) is an image including the face of a specific person A looking straight ahead, the second reference image (20-3) may be an image including the face of a specific person A looking sideways.

[0088] Additionally, the computing device (100) can calculate the first similarity between the first reference image (20-1) and the first frame image (10-1) as 0.9, and can calculate the second similarity between the second reference image (20-3) and the second frame image (10-3) as 0.8. Specifically, the computing device (100) can calculate the first similarity between the “first reference image (20-1) and the first frame image (10-1) in which the person included in the image is looking straight ahead” as 0.9, and the second similarity between the “second reference image (20-3) and the second frame image (10-3) in which the person included in the image is looking sideways” as 0.8. Through this, the computing device (100) can compare the front and front and the side and the side of the first and second reference images (20-1 and 20-3) and the first and second frame images (10-1 and 10-3) to calculate the similarity, thereby compensating for errors due to the difference in angles between the objects of the similarity calculation and increasing the accuracy of the similarity calculation. Thereafter, the computing device (100) can calculate the target video (10-1 to 10-3) based on the calculated first and second similarities. 10-4) can be predicted as to whether or not the content is false, and the examples described above can be utilized in this regard. In relation to this, in the case of a technology for changing a face, such as a face swap, the face is changed by utilizing an image close to the front, so the greater the difference in the face shape or angle between the person whose face is changed and the person, the lower the quality of the changed face, and the lower the naturalness of the changed face. Therefore, the first similarity (0.9) calculated between the first reference image (20-1) and the first frame image (10-1) facing the front is higher than the second similarity (0.9) calculated between the second reference image (20-3) and the second frame image (10-3) facing the side.8) If the target video (10-1 to 10-4) is higher, the computing device (100) can detect the target video (10-1 to 10-4) as false content. Meanwhile, the computing device (100) can use the reference similarity to predict whether the target video (10-1 to 10-4) is false content, and this will be described later with reference to FIG. 6.

[0089]

[0090] FIG. 6 is a schematic diagram illustrating a process of calculating a reference similarity between a first reference image and a second reference image, calculating a second similarity between the first reference image and a second frame image, and predicting whether the target video contains false content based on the similarity.

[0091] Referring to FIG. 6, the computing device (100) can calculate the reference similarity between the first reference image (20-1) and the second reference image (20-3) as 0.8, and can calculate the second' similarity between the first reference image (20-1) and the second frame image (10-3) as 0.6. In this regard, since the first reference image (20-1) and the second reference image (20-3) are images included in a reference video for a specific person A, the calculated similarity between the first reference image (20-1) and the second reference image (20-3) can be set as a reference similarity that takes into account the difference according to the angle of the same person looking at the front and the side. In contrast, since the second frame image (10-3) is an image included in the target video that is the target of the determination of the authenticity of the false content, the second similarity calculated between the first reference image (20-1) and the second frame image (10-3) can be utilized in the process of the computing device (100) determining the authenticity of the false content of the target videos (10-1 to 10-4) by comparing it with the calculated reference similarity. Thereafter, the computing device (100) can predict whether the target videos (10-1 to 10-4) are false content based on the calculated reference similarity and the second similarity. Specifically, the computing device (100) can calculate the difference between the calculated reference similarity and the second similarity, and predict whether the target videos are false content based on the difference in the calculated similarities. For example, the computing device (100) can predict the target video as false content if the second similarity decreases from the calculated reference similarity (0.8) to 0.6. As another example, the computing device (100) can predict the target video as false content if the difference between the calculated reference similarity and the second similarity, which is 0.2, is less than the preset threshold of 0.If the number is 2 or more, the target video (10-1 to 10-4) can be predicted as false content. Accordingly, the computing device (100) according to one embodiment of the present disclosure can more accurately detect false content by utilizing the facial angle of the person included in the video by predicting the target video as false content when the similarity between the person included in the reference image and the target video (10-1 to 10-3) is calculated differently depending on the angle.

[0092]

[0093] According to one embodiment of the present disclosure, a computer-readable medium storing a data structure is disclosed. A data structure can refer to the organization, management, and storage of data that enables efficient access and modification of the data. A data structure can refer to the organization of data to solve a specific problem (e.g., data retrieval, data storage, or data modification in the shortest possible time). A data structure can also be defined as a physical or logical relationship between data elements designed to support a specific data processing function. A logical relationship between data elements can include a connection relationship between user-defined data elements. A physical relationship between data elements can include an actual relationship between data elements physically stored in a computer-readable storage medium (e.g., a persistent storage device). A data structure can specifically include a set of data, relationships between data, and functions or commands applicable to the data. An effectively designed data structure enables a computing device to perform operations while minimizing the use of its resources. Specifically, a computing device can improve the efficiency of operations, reading, insertion, deletion, comparison, exchange, and searching through an effectively designed data structure.

[0094] Data structures can be categorized as linear or nonlinear, depending on their form. A linear data structure can be a structure in which only one data item is linked to the next. Linear data structures can include lists, stacks, queues, and deques. A list can refer to a series of data sets with an internal order. Lists can also include linked lists. A linked list is a data structure in which data is linked in a single line, each item having a pointer. In a linked list, a pointer can contain information about the next or previous item. Linked lists can be expressed as singly linked lists, doubly linked lists, or circular linked lists, depending on their form. A stack can be a data listing structure with limited data access. A stack can be a linear data structure in which data operations (e.g., insertion or deletion) can only be performed at one end of the data structure. Data stored in a stack can be a Last-in-First-out (LIFO) data structure. A queue is a data structure with limited access to data. Unlike a stack, it can be a first-in, first-out (FIFO) data structure, with later data being retrieved later. A deck can be a data structure that can process data at both ends.

[0095] A nonlinear data structure can be a structure in which multiple pieces of data are connected behind a single piece of data. Nonlinear data structures can include graph data structures. A graph data structure can be defined by vertices and edges, and an edge can include a line connecting two different vertices. Graph data structures can include tree data structures. A tree data structure can be a data structure in which there is only one path connecting two different vertices among multiple vertices included in the tree. In other words, it can be a data structure that does not form a loop in a graph data structure.

[0096] Throughout this specification, the terms computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, they are collectively referred to as neural networks. The data structure may include a neural network. And the data structure including the neural network may be stored on a computer-readable medium. The data structure including the neural network may also include preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. The data structure including the neural network may include any of the components disclosed above. That is, the data structure including the neural network may be configured to include all or any combination of preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. In addition to the aforementioned configurations, a data structure including a neural network may include any other information that determines the characteristics of the neural network. Furthermore, the data structure may include any form of data used or generated in the computational process of the neural network, and is not limited to the aforementioned. The computer-readable medium may include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node.

[0097] The data structure may include data input to a neural network. The data structure including the data input to the neural network may be stored on a computer-readable medium. The data input to the neural network may include training data input during the neural network training process and / or input data input to the neural network after training has been completed. The data input to the neural network may include data that has undergone preprocessing and / or data that is the target of preprocessing. Preprocessing may include a data processing process for inputting data to the neural network. Accordingly, the data structure may include data that is the target of preprocessing and data generated by the preprocessing. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

[0098] The data structure may include weights of the neural network. (In this specification, the terms "weight" and "parameter" may be used interchangeably.) The data structure including the weights of the neural network may be stored in a computer-readable medium. The neural network may include a plurality of weights. The weights may be variable and may be varied by a user or an algorithm so that the neural network can perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node may determine a data value output from the output node based on values ​​input to the input nodes connected to the output node and weights set for links corresponding to each input node. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

[0099] By way of example and not limitation, the weights may include weights that vary during the neural network training process and / or weights that have completed neural network training. The weights that vary during the neural network training process may include weights at the start of the training cycle and / or weights that vary during the training cycle. The weights that have completed neural network training may include weights that have completed the training cycle. Accordingly, a data structure including the weights of a neural network may include a data structure including weights that vary during the neural network training process and / or weights that have completed neural network training. Therefore, the above-described weights and / or combinations of each weight are included in the data structure including the weights of a neural network. The above-described data structures are merely examples and the present disclosure is not limited thereto.

[0100] A data structure including neural network weights can be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be a process of converting a data structure into a form that can be stored on the same or different computing devices and later reconstructed and used. A computing device can serialize the data structure to transmit and receive data over a network. The serialized data structure including neural network weights can be reconstructed on the same or different computing devices through deserialization. The data structure including neural network weights is not limited to serialization. Furthermore, the data structure including neural network weights can include a data structure that increases computational efficiency while minimizing the use of computing device resources (e.g., a B-Tree, a Trie, an m-way search tree, an AVL tree, a Red-Black Tree in nonlinear data structures). The foregoing is merely an example, and the present disclosure is not limited thereto.

[0101] The data structure may include hyperparameters of a neural network. Furthermore, the data structure including the hyperparameters of the neural network may be stored on a computer-readable medium. The hyperparameters may be variables that can be varied by the user. The hyperparameters may include, for example, a learning rate, a cost function, the number of learning cycle repetitions, weight initialization (e.g., setting a range of weight values ​​to be subject to weight initialization), and the number of hidden units (e.g., the number of hidden layers, the number of nodes in the hidden layer). The above-described data structure is merely an example, and the present disclosure is not limited thereto.

[0102]

[0103] FIG. 7 is a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0104] Although the present disclosure has been described above as being generally implemented by a computing device, those skilled in the art will appreciate that the present disclosure may also be implemented in combination with computer-executable instructions and / or other program modules that may be executed on one or more computers and / or as a combination of hardware and software.

[0105] Generally, program modules include routines, programs, components, data structures, and the like that perform specific tasks or implement specific abstract data types. Furthermore, those skilled in the art will appreciate that the methods of the present disclosure can be implemented with other computer system configurations, including single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like, each of which may be operatively connected to one or more associated devices.

[0106] The described embodiments of the present disclosure can also be practiced in distributed computing environments, where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0107] Computers typically include a variety of computer-readable media. Computer-readable media can be any media that can be accessed by a computer, and includes both volatile and nonvolatile media, transitory and non-transitory media, removable and non-removable media. By way of example, and not limitation, computer-readable media can include computer-readable storage media and computer-readable transmission media. Computer-readable storage media includes both volatile and nonvolatile media, transitory and non-transitory media, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be accessed by a computer and used to store the desired information.

[0108] Computer-readable transmission media typically includes any information delivery media that embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism. The term modulated data signal means a signal that has one or more of its characteristics set or changed so as to encode information in the signal. By way of example, and not limitation, computer-readable transmission media includes wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared, or other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

[0109] An exemplary environment (1100) implementing various aspects of the present disclosure is illustrated, including a computer (1102) comprising a processing unit (1104), system memory (1106), and a system bus (1108). The system bus (1108) connects system components, including but not limited to the system memory (1106), to the processing unit (1104). The processing unit (1104) may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be utilized as the processing unit (1104).

[0110] The system bus (1108) may be any of several types of bus structures that may be additionally interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. The system memory (1106) includes read-only memory (ROM) (1110) and random access memory (RAM) (1112). A basic input / output system (BIOS) is stored in non-volatile memory (1110), such as ROM, EPROM, or EEPROM, and includes basic routines that help transfer information between components within the computer (1102), such as during start-up. The RAM (1112) may also include high-speed RAM, such as static RAM, for caching data.

[0111] The computer (1102) also includes an internal hard disk drive (HDD) (1114) (e.g., EIDE, SATA) - which may also be configured for external use within a suitable chassis (not shown), a magnetic floppy disk drive (FDD) (1116) (e.g., for reading from or writing to a removable diskette (1118)), and an optical disk drive (1120) (e.g., for reading from or writing to a CD-ROM disk (1122) or other high-capacity optical media such as a DVD). The hard disk drive (1114), the magnetic disk drive (1116), and the optical disk drive (1120) may be connected to the system bus (1108) by a hard disk drive interface (1124), a magnetic disk drive interface (1126), and an optical drive interface (1128), respectively. The interface (1124) for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

[0112] These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. In the case of the computer (1102), the drives and media correspond to storing any data in a suitable digital format. While the description of computer-readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those of ordinary skill in the art will appreciate that other types of computer-readable media, such as zip drives, magnetic cassettes, flash memory cards, cartridges, and the like, may also be used in the exemplary operating environment, and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

[0113] A number of program modules, including an operating system (1130), one or more application programs (1132), other program modules (1134), and program data (1136), may be stored in the drive and RAM (1112). All or portions of the operating system, applications, modules, and / or data may also be cached in RAM (1112). It will be appreciated that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

[0114] A user may enter commands and information into the computer (1102) via one or more wired / wireless input devices, such as a keyboard (1138) and a pointing device such as a mouse (1140). Other input devices (not shown) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, and the like. These and other input devices are often connected to the processing unit (1104) via an input device interface (1142) that is connected to the system bus (1108), but may be connected by other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, and the like.

[0115] A monitor (1144) or other type of display device is also connected to the system bus (1108) via an interface, such as a video adapter (1146). In addition to the monitor (1144), the computer typically includes other peripheral output devices (not shown), such as speakers, a printer, and so on.

[0116] The computer (1102) may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) (1148), via wired and / or wireless communications. The remote computer(s) (1148) may be a workstation, a computing device computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other conventional network node, and generally include many or all of the components described for the computer (1102), although for simplicity, only the memory storage device (1150) is shown. The logical connections shown include wired / wireless connections to a local area network (LAN) (1152) and / or a larger network, such as a wide area network (WAN) (1154). Such LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which may be connected to a worldwide computer network, such as the Internet.

[0117] When used in a LAN networking environment, the computer (1102) is connected to a local network (1152) via a wired and / or wireless communication network interface or adapter (1156). The adapter (1156) may facilitate wired or wireless communications to the LAN (1152), which may also include a wireless access point installed therein for communicating with the wireless adapter (1156). When used in a WAN networking environment, the computer (1102) may include a modem (1158), be connected to a communications computing device on the WAN (1154), or have other means of establishing communications over the WAN (1154), such as via the Internet. The modem (1158), which may be internal or external and wired or wireless, is connected to the system bus (1108) via a serial port interface (1142). In a networked environment, program modules or portions thereof described for the computer (1102) may be stored in a remote memory / storage device (1150). It will be appreciated that the network connections depicted are exemplary and other means of establishing a communications link between the computers may be used.

[0118] The computer (1102) operates to communicate with any wireless device or object that is arranged and operates via wireless communication, such as a printer, a scanner, a desktop and / or portable computer, a portable data assistant (PDA), a communication satellite, any equipment or location associated with a radio-detectable tag, and a telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network, or may simply be an ad hoc communication between at least two devices.

[0119] Wi-Fi (Wireless Fidelity) enables connections to the Internet and other devices without wires. Wi-Fi is a wireless technology that allows devices, such as computers, to send and receive data anywhere within the coverage area of ​​a base station, both indoors and outdoors, similar to cell phones. Wi-Fi networks use wireless technologies called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz radio bands, at data rates of, for example, 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual-band).

[0120] Those skilled in the art will appreciate that information and signals may be represented using any of a variety of different technologies and techniques. For example, the data, instructions, commands, information, signals, bits, symbols, and chips referenced in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0121] Those skilled in the art will appreciate that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, various forms of programs or design code (referred to herein, for convenience, as software), or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0122] The various embodiments presented herein can be implemented as a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Furthermore, various storage media presented herein include one or more devices and / or other machine-readable media for storing information.

[0123] It should be understood that the specific order or hierarchy of steps in the presented processes is merely an example of exemplary approaches. It should be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present disclosure based on design priorities. The appended method claims provide elements of various steps in a sample order, but are not intended to be limited to the specific order or hierarchy presented.

[0124] The description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments disclosed herein, but is to be construed in the broadest scope consistent with the principles and novel features disclosed herein.

[0125] As described above, the relevant contents have been described in the best form for carrying out the invention.

Claims

1. A method for detecting false content, performed by one or more processors of a computing device, A step of acquiring a target video including a reference image and a person; A step of obtaining a first frame image included in the target video and a second frame image different from the first frame image; A step of calculating a first similarity between the reference image and the first frame image, and calculating a second similarity between the reference image and the second frame image; and A step of predicting whether the target video is false content based on the calculated first similarity and the second similarity; Including, method.

2. In paragraph 1, The step of obtaining a first frame image included in the above target video and a second frame image different from the first frame image is: Comprising a step of obtaining a first frame image included in the target video and a second frame image including a face of a person included in the first frame image at different angles, method.

3. In paragraph 2, The step of obtaining a first frame image included in the above target video and a second frame image including a face of a person included in the first frame image at different angles, A step of acquiring a first frame image including a face of a person having an angle within a preset threshold based on the front; and A step of acquiring a second frame image including a face of a person having an angle exceeding a preset threshold with respect to the front; Including, method.

4. In paragraph 1, The step of obtaining a first frame image included in the above target video and a second frame image different from the first frame image is: A step of performing super resolution processing on at least one of the acquired first frame image or the acquired second frame image; Including more, method.

5. In paragraph 1, The step of calculating a first similarity between the reference image and the first frame image, and calculating a second similarity between the reference image and the second frame image, A step of performing encoding on the reference image using a neural network model and obtaining a reference encoding vector; A step of performing encoding on the first frame image by utilizing the neural network model to obtain a first encoding vector, and performing encoding on the second frame image to obtain a second encoding vector; and A step of calculating a first similarity between the reference encoding vector and the first encoding vector, and calculating a second similarity between the reference encoding vector and the second encoding vector; Including, method.

6. In paragraph 5, The above neural network model is, Contains a pre-trained model to extract identity features from facial images of people. method.

7. In paragraph 1, The above reference image is, Contains images obtained from a reference video containing a specific person; method.

8. In paragraph 7, The above reference image is, A first reference image included in the above reference video and a second reference image included in the above reference video that is different from the first reference image, The step of calculating a first similarity between the reference image and the first frame image, and calculating a second similarity between the reference image and the second frame image, Comprising the step of calculating a first similarity between the first reference image and the first frame image, and calculating a second similarity between the second reference image and the second frame image. method.

9. In paragraph 7, The above reference image is, A first reference image included in the above reference video and a second reference image included in the above reference video that is different from the first reference image, The step of calculating a first similarity between the reference image and the first frame image, and calculating a second similarity between the reference image and the second frame image, Comprising the step of calculating a reference similarity between the first reference image and the second reference image, and calculating a second similarity between the first reference image and the second frame image. method.

10. In paragraph 1, The step of predicting whether the target video is false content based on the calculated first similarity and the second similarity is as follows: a step of calculating the difference between the calculated first similarity and the second similarity; and A step of predicting whether the target video is false content based on the difference in the calculated similarity; Including, method.

11. In Article 10, The step of predicting whether the target video contains false content based on the difference in the calculated similarity is as follows: A step of predicting the target video as false content when the second similarity decreases compared to the calculated first similarity, method.

12. In paragraph 10, The step of predicting whether the target video contains false content based on the difference in the calculated similarity is as follows: A step of predicting the target video as false content if the difference in the calculated similarity is greater than a preset threshold, method.

13. A computer program stored in a computer-readable storage medium, wherein the computer program, when executed by one or more processors, causes the one or more processors to perform operations for detecting false content, the operations comprising: An action of acquiring a target video containing a reference image and a person; An operation of obtaining a first frame image included in the target video and a second frame image different from the first frame image; An operation of calculating a first similarity between the reference image and the first frame image, and calculating a second similarity between the reference image and the second frame image; and An operation of predicting whether the target video is false content based on the calculated first similarity and the second similarity; Including, A computer program stored on a computer-readable storage medium.

14. As a computing device, at least one processor; and Memory Including, At least one processor of the above, Acquire a target video containing a reference image and a person; Obtaining a first frame image included in the target video and a second frame image different from the first frame image; Computing a first similarity between the reference image and the first frame image, and calculating a second similarity between the reference image and the second frame image; and configured to predict whether the target video is a false content based on the calculated first similarity and the second similarity. Computing device.

15. A data structure included in a computer-readable storage medium, wherein the data structure corresponds to parameters of a neural network, and the neural network performs the following steps at least partially based on the parameters, wherein the steps include: A step of acquiring a target video including a reference image and a person; A step of obtaining a first frame image included in the target video and a second frame image different from the first frame image; A step of calculating a first similarity between the reference image and the first frame image, and calculating a second similarity between the reference image and the second frame image; and A step of predicting whether the target video is false content based on the calculated first similarity and the second similarity; Including, A data structure contained in a computer-readable storage medium.

Images