KR20230018316A - Method for restoring a masked face image by using the neural network model - Google Patents

Abstract

Disclosed is a method for restoring a masked face image performed by one or more processors of a computing device according to an embodiment of the present disclosure. The method may include the steps of: identifying a masked face image included in a restoration target image; acquiring an unmasked face image of a person associated with the identified masked face image; and synthesizing the obtained masked face image with the identified unmasked face image.

Description

A method for restoring a face image wearing a mask using a neural network model {METHOD FOR RESTORING A MASKED FACE IMAGE BY USING THE NEURAL NETWORK MODEL}

The present disclosure relates to a technology for modifying a face image with a mask on, and more particularly, to a technology for converting a face image with a mask on into a face image with the mask removed.

Recently, due to COVID-19, a photo shoot is being done while wearing a mask. For example, even in commemorative events such as weddings, graduation ceremonies, and entrance ceremonies, photos are taken while wearing a mask regardless of the person's intention. Accordingly, there is an increasing demand for a technology that changes a face wearing a mask on a photo to a face before wearing the mask.

In this regard, research has been conducted to remove the mask from a mask wearing photo, but it is impossible to restore the same person in the process of generating a photo of the area covered by the mask, and it is impossible to restore the same person, including a plurality of people, or because the face area is aligned. If not, there were problems that made it difficult to obtain good results.

Therefore, a new technique capable of solving these problems is required.

An object of the present disclosure is to provide a technology capable of converting a mask-wearing face image into a mask-removed face image using a neural network model.

A method performed by a computing device according to an embodiment of the present disclosure for realizing the above object is disclosed. The method may include identifying a face image wearing a mask included in a restoration target image; acquiring a face image of a person associated with the identified face image wearing a mask without wearing a mask; and synthesizing the obtained mask-wearing face image with the identified mask-wearing face image.

Alternatively, the synthesizing of the obtained mask-wearing face image with the identified mask-wearing face image may include converting the identified mask-wearing face image into a virtual face image from which the mask is removed by using a first neural network model. doing; and applying a face image conversion technique from the virtual face image from which the mask is removed to the acquired face image without a mask, using a second neural network model.

Alternatively, the step of converting the identified mask-wearing face image into a virtual face image from which the mask is removed by using the first neural network model may include using a generative adversarial networks (GAN) generation model, The method may include converting a mask-wearing face image into a virtual face image from which the mask is removed.

Alternatively, identifying the mask-wearing face image included in the restoration target image may include identifying and identifying a partial region including the mask-wearing face image in the restoration target image.

Alternatively, the synthesizing of the obtained face image not wearing a mask with the identified face image wearing a mask may include a partial region including the identified face image wearing a mask within the reconstruction target image by using a neural network model. It may include applying a face image conversion technique to the obtained mask-unwearing face image for .

Alternatively, identifying the mask-wearing face image included in the restoration target image may include identifying a plurality of mask-wearing face images included in the restoration target image.

Alternatively, acquiring a mask-unwearing face image of a person associated with the identified mask-wearing face image may include acquiring a plurality of mask-unwearing face images of a plurality of persons associated with the plurality of mask-wearing face images. steps may be included.

Alternatively, the synthesizing of the obtained mask-wearing face image with the identified mask-wearing face image may include combining each of the obtained plurality of mask-wearing face images with each of the identified plurality of mask-wearing face images. steps may be included.

Alternatively, the step of synthesizing each of the obtained plurality of face images not wearing a mask with each of the plurality of identified face images wearing a mask may include using a first neural network model to obtain a plurality of identified face images wearing a mask. converting the virtual face images into a plurality of virtual face images from which the mask is removed; and applying a face image conversion technique from each of the plurality of virtual face images from which the mask is removed to each of the obtained plurality of mask-unwearing face images by utilizing a second neural network model.

A computer program stored in a computer readable storage medium is disclosed according to an embodiment of the present disclosure for realizing the above object. When the computer program is executed in one or more processors, the one or more processors cause the one or more processors to perform operations for reconstructing a mask-wearing face image, the operations comprising: identifying a mask-wearing face image included in a reconstruction target image. ; acquiring a face image of a person associated with the identified face image wearing a mask without wearing a mask; and combining the obtained face image not wearing a mask with the identified face image wearing a mask.

A computing device according to an embodiment of the present disclosure for realizing the above object is disclosed. The device may include at least one processor; and a memory, wherein the processor is configured to: identify a face image wearing a mask included in a restoration target image; obtaining a face image of a person associated with the identified face image wearing a mask without wearing a mask; And it may be configured to synthesize the obtained mask-free face image to the identified mask-wearing face image.

The present disclosure may provide a technology capable of converting a face image with a mask on into a face image with the mask removed by using a neural network model.

1 is a block diagram of a computing device for synthesizing a face image using a face image conversion technique using a neural network model according to an embodiment of the present disclosure.
2 is a schematic diagram illustrating a network function according to an embodiment of the present disclosure.
3 is a flowchart illustrating a process of synthesizing a face image using a face image conversion technique using a neural network model according to an embodiment of the present disclosure.
4 is a schematic diagram illustrating a method of synthesizing a face image using a face image conversion technology using a neural network model according to an embodiment of the present disclosure.
5 is a flowchart illustrating a process of partially synthesizing a face image using a face image conversion technique using a neural network model according to an embodiment of the present disclosure.
6 is a schematic diagram illustrating a method of partially synthesizing a face image using a face image conversion technique using a neural network model according to an embodiment of the present disclosure.
7 is a schematic diagram illustrating a method of synthesizing a plurality of face images using a face image conversion technique using a neural network model according to an embodiment of the present disclosure.
8 is a simplified and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the present disclosure. However, it is apparent that these embodiments may be practiced without these specific details.

The terms “component,” “module,” “system,” and the like, as used herein, refer to a computer-related entity, 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, processor, object, thread of execution, program, and/or computer running on a processor. For example, both an application running on a computing device and a computing device may be components. One or more components may reside within a processor and/or thread of execution. A component can be localized within a single computer. A component may be distributed between two or more computers. Also, these components can execute from various computer readable media having various data structures stored thereon. Components may be connected, for example, via signals with one or more packets of data (e.g., data and/or signals from one component interacting with another component in a local system, distributed system) to other systems and over a network such as the Internet. data being transmitted) may communicate via local and/or remote processes.

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless otherwise specified or clear from the context, “X employs A or B” is intended to mean one of the natural inclusive substitutions. That is, X uses A; X uses B; Or, if X uses both A and B, "X uses either A or B" may apply to either of these cases. Also, the term "and/or" as used herein should be understood to refer to and include all possible combinations of one or more of the listed related items.

Also, the terms "comprises" and/or "comprising" should be understood to mean that the features and/or components are present. 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, elements, and/or groups thereof. Also, unless otherwise specified or where the context clearly indicates that a singular form is indicated, the singular in this specification and claims should generally be construed to mean "one or more".

In addition, the term “at least one of A or B” should be interpreted as meaning “when only A is included”, “when only B is included”, and “when A and B are combined”.

Those skilled in the art will further understand that the various illustrative logical blocks, components, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented using electronic hardware, computer software, or combinations of both. It should be recognized that it can be implemented as 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 in hardware or as software depends on 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 this disclosure.

The description of the presented embodiments is provided to enable any person skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art of this disclosure. The general principles defined herein may be applied to other embodiments without departing from the scope of this disclosure. Thus, the present invention is not limited to the embodiments presented herein. The present invention is to be accorded the widest scope consistent with the principles and novel features set forth herein.

In the present disclosure, network functions, artificial neural networks, and neural networks may be used interchangeably.

1 is a block diagram of a computing device for synthesizing a face image using a face image conversion technique using a neural network model according to an embodiment of the present disclosure.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device 100 may include other components for performing a computing environment of the computing device 100, and only some of the disclosed components may constitute the computing device 100.

The computing device 100 may include a processor 110 , a memory 130 , and a network unit 150 .

The processor 110 may include one or more cores, and includes a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit), data analysis, and processors for deep learning. The processor 110 may read a computer program stored in the memory 130 and process data for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning a neural network. The processor 110 is used for neural network learning, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating neural network weights using backpropagation. calculations can be performed. At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, the CPU and GPGPU can process learning of network functions and data classification using network functions. In addition, in an embodiment of the present disclosure, the learning of a network function and data classification using a network function may be processed by using processors of a plurality of computing devices together. In addition, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU or TPU executable program.

The processor 110 according to an embodiment of the present disclosure identifies a mask-wearing face image included in a reconstruction target image to restore a mask-wearing face image, and generates a mask-unwearing face image of a person associated with the identified mask-wearing face image. and synthesizing the obtained face image not wearing a mask with the identified face image wearing a mask. In addition, the process of acquiring the face image of the related person without a mask is based on the “similarity of the facial area other than wearing a mask in the image to be restored” with the “photo of the face without a mask provided in advance”. A process of matching face images not wearing a mask may be included. Additionally, according to an embodiment of the present disclosure, when identifying a face image wearing a mask included in the reconstruction target image, the processor 110 distinguishes a partial region including the mask wearing face image from the reconstruction target image. can be identified.

According to an embodiment of the present disclosure, the processor 110, when synthesizing the obtained mask-wearing face image with the identified mask-wearing face image, uses a first neural network model to obtain the identified mask-wearing face image. A technology for converting to a virtual face image from which the mask is removed, and converting the mask-removed virtual face image into the obtained mask-unwearing face image by using a second neural network model (ie, “face image conversion technology”) It is possible to perform an operation to apply . In this case, the first neural network model and the second neural network model may be configured separately or configured as a single neural network according to an embodiment. In addition, facial image conversion technology using a neural network model may include artificial intelligence-based image synthesis technologies such as deep fake, face 2 face, face swap, neural textures, and pristine. In addition, when converting the identified mask-wearing face image into a virtual face image from which the mask is removed by using a neural network model, the processor 110 utilizes a generative adversarial networks (GAN) model to convert the identified mask face image into a virtual face image from which the mask is removed. The wearing face image may be converted into a virtual face image from which the mask is removed.

Additionally, according to an embodiment of the present disclosure, the processor 110, when synthesizing the obtained mask-unwearing face image with the identified mask-wearing face image, uses a neural network model to distinguish and identify within the restoration target image. The face image conversion technology may be applied to a partial region including a mask-wearing face image.

Also, according to an embodiment of the present disclosure, when identifying a face image wearing a mask included in the restoration target image, the processor 110 may identify a plurality of mask wearing face images included in the restoration target image. . Also, the processor 110 may obtain a plurality of mask-unwearing face images of a plurality of persons related to the identified plurality of mask-wearing face images. Additionally, the processor 110 may synthesize each of the obtained plurality of face images not wearing a mask with each of the plurality of identified face images wearing a mask.

In this case, according to an embodiment of the present disclosure, the processor 110 utilizes a first neural network model when synthesizing each of the obtained plurality of face images not wearing a mask with each of the plurality of identified face images wearing a mask. Thus, the identified plurality of mask-wearing face images are converted into a plurality of virtual face images from which the mask is removed, and each of the plurality of virtual face images from which the mask is removed is converted into a plurality of virtual face images from which the mask is removed by using a second neural network model. It can be converted into each of the mask-unwearing face images of . In this case, the first neural network model and the second neural network model may be configured separately or configured as a single neural network according to an embodiment.

According to an embodiment of the present disclosure, the memory 130 may store any type of information generated or determined by the processor 110 and any type of information received by the network unit 150 .

According to an embodiment of the present disclosure, the memory 130 is a flash memory type, a hard disk type, a multimedia card micro type, or a card type memory (eg, SD or XD memory, etc.), RAM (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory) -Only Memory), a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium. The computing device 100 may operate in relation to a web storage that performs a storage function of the memory 130 on the Internet. The above description of the memory is only an example, and the present disclosure is not limited thereto.

The network unit 150 according to an embodiment of the present disclosure may use any type of known wired or wireless communication system.

For example, the network unit 150 may receive information on an image to be restored from an external system. In this case, the information received from the database may be data for synthesizing a face image using a face image conversion technology using a neural network model. The information of the image to be restored may include the information of the above-described example, but is not limited to the above-described example and may be configured in various ways within a range that a person skilled in the art can understand.

In addition, the network unit 150 may transmit and receive information processed by the processor 110, a user interface, and the like through communication with other terminals. For example, the network unit 150 may provide a user interface generated by the processor 110 to a client (eg, a user terminal). In addition, the network unit 150 may receive an external input of a user authorized as a client and transmit it to the processor 110 . At this time, the processor 110 may process operations such as outputting, correcting, changing, adding, and the like of information provided through the user interface based on the user's external input received from the network unit 150 .

Meanwhile, the computing device 100 according to an embodiment of the present disclosure may include a server as a computing system that transmits and receives information through communication with a client. In this case, the client may be any type of terminal capable of accessing the server. For example, the computing device 100 as a server may receive information for restoring a face image wearing a mask from an external database, generate a face image synthesis result, and provide a user interface related to the face image synthesis result to a user terminal. . In this case, the information for restoration may include a face image not wearing a mask manually provided by the user or an image automatically provided from the photo album. In addition, the user terminal may output a user interface received from the computing device 100, which is a server, and receive or process information through interaction with the user.

In an additional embodiment, the computing device 100 may include any type of terminal that receives data resources generated by any server and performs additional information processing.

2 is a schematic diagram illustrating a network function according to an embodiment of the present disclosure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. A neural network may consist 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 includes one or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more links.

In a neural network, one or more nodes connected through a link may form a relative relationship of an input node and an output node. The concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa. As described above, an input node to output node relationship may be created around a link. More than one output node can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of data of the output node may be determined based on data input to the input node. Here, a link interconnecting an input node and an output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order to perform a function desired by the neural network. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. An output node value may be determined based on the weight.

As described above, in the neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship in the neural network. Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association between the nodes and links, and a weight value assigned to each link. For example, when there are two neural networks having the same number of nodes and links and different weight values of the links, the two neural networks may be recognized as different from each other.

A neural network may be composed of a set of one or more nodes. A subset of nodes constituting a neural network may constitute a layer. Some of the nodes constituting the neural network may form one layer based on distances from the first input node. For example, a set of nodes having a distance of n from the first input node may constitute n layers. The distance from the first input node may be defined by the minimum number of links that must be passed through to reach the corresponding node from the first input node. However, the definition of such a layer is arbitrary for explanation, and the order of a layer in a neural network may be defined in a method different from the above. For example, a layer of nodes may be defined by a distance from a final output node.

An initial input node may refer to one or more nodes to which data is directly input without going through a link in relation to other nodes among nodes in the neural network. Alternatively, in a relationship between nodes based on a link in a neural network, it may mean nodes that do not have other input nodes connected by a link. Similarly, the final output node may refer to one or more nodes that do not have an output node in relation to other nodes among nodes in the neural network. Also, the hidden node may refer to nodes constituting the neural network other than the first input node and the last output node.

In the neural network according to an embodiment of the present disclosure, the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as the number of nodes progresses from the input layer to the hidden layer. can In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes of the input layer may be less than the number of nodes of the output layer and the number of nodes decreases as the number of nodes increases from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure is a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as the number of nodes increases from the input layer to the hidden layer. can A neural network according to another embodiment of the present disclosure may be a neural network in the form of a combination of the aforementioned neural networks.

A deep neural network (DNN) may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can reveal latent structures in data. In other words, it can identify the latent structure of a photo, text, video, sound, or music (e.g., what objects are in the photo, what the content and emotion of the text are, what the content and emotion of the audio are, etc.). . Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, generative adversarial networks (GANs), and restricted boltzmann machines (RBMs). machine), a deep belief network (DBN), a Q network, a U network, a Siamese network, a Generative Adversarial Network (GAN), and the like. The description of the deep neural network described above is only an example, and the present disclosure is not limited thereto.

In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network for outputting output data similar to input data. An auto-encoder may include at least one hidden layer, and an odd number of hidden layers may be disposed between input and output layers. The number of nodes of each layer may be reduced from the number of nodes of the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically with the reduction from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform non-linear dimensionality reduction. The number of input layers and output layers may correspond to dimensions after preprocessing of input data. In the auto-encoder structure, the number of hidden layer nodes included in the encoder may decrease as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, a sufficient amount of information may not be conveyed, so more than a certain number (e.g., more than half of the input layer, etc.) ) may be maintained.

The neural network may be trained using at least one of supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Learning of the neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

A neural network can be trained in a way that minimizes output errors. In the learning of the neural network, the learning data is repeatedly input into the neural network, the output of the neural network for the training data and the error of the target are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. It is a process of updating the weight of each node of the neural network by backpropagating in the same direction. In the case of teacher learning, the learning data in which the correct answer is labeled is used for each learning data (ie, the labeled learning data), and in the case of comparative teacher learning, the correct answer may not be labeled in each learning data. That is, for example, learning data in the case of teacher learning regarding data classification may be data in which each learning data is labeled with a category. Labeled training data is input to a neural network, and an error may be calculated by comparing an output (category) of the neural network and a label of the training data. As another example, in the case of comparative history learning for data classification, an error may be calculated by comparing input learning data with a neural network output. The calculated error is back-propagated in a reverse direction (ie, from the output layer to the input layer) in the neural network, and the connection weight of each node of each layer of the neural network may be updated according to the back-propagation. The amount of change in the connection weight of each updated node may be determined according to a learning rate. The neural network's computation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of iterations of the learning cycle of the neural network. For example, a high learning rate may be used in the early stage of neural network training to increase efficiency by allowing the neural network to quickly obtain a certain level of performance, and a low learning rate may be used in the late stage to increase accuracy.

In neural network learning, generally, training data can be a subset of real data (ie, data to be processed using the trained neural network), and therefore, errors for training data are reduced, but errors for real data are reduced. There may be incremental learning cycles. Overfitting is a phenomenon in which errors for actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that has learned a cat by showing a yellow cat does not recognize that it is a cat when it sees a cat other than yellow may be a type of overfitting. Overfitting can act as a cause of increasing the error of machine learning algorithms. Various optimization methods can be used to prevent such overfitting. To prevent overfitting, methods such as increasing the training data, regularization, inactivating some nodes in the network during learning, and using a batch normalization layer should be applied. can

Reinforcement learning is a learning method in which a neural network model is trained based on a reward calculated for an action selected by the neural network model so that the neural network model can determine a better action based on the state. A state is a set of values representing how the situation is at the current point in time, and can be understood as an input to a neural network model. An action refers to a decision based on the options that a neural network model can take, and can be understood as an output of a neural network model. Reward refers to a benefit that follows when a neural network model performs a certain action, and represents a value evaluated for the current state and action. Reinforcement learning can be understood as learning through trial and error in that a reward is given for an action. A reward given to a neural network model in a reinforcement learning process may be a reward obtained by accumulating results of various actions. Through reinforcement learning, it is possible to create a neural network model that maximizes a return such as the reward itself or the sum of the rewards by considering rewards according to various states and actions.

3 is a flowchart illustrating a process of synthesizing a face image using a face image conversion technique using a neural network model according to an embodiment of the present disclosure.

Referring to FIG. 3 , the computing device 100 according to an embodiment of the present disclosure may acquire restoration target image information from internal storage or receive restoration target image information from an external system (S110). The external system may be a server, database, or the like that stores and manages information for restoring an image of a face wearing a mask. The computing device 100 may use information received from an external system as input data for restoring an image of a face wearing a mask. The computing device 100 may use information received from an external system as input data for restoring a face image wearing a mask. The use pattern of such information may vary according to the purpose of restoring a face image wearing a mask.

In addition, the computing device 100 may identify a mask-wearing face image included in the received restoration target image, and obtain a mask-free face image of a person associated with the identified mask-wearing face image (S120).

In addition, the computing device 100 may convert the mask-wearing face image identified through step S120 into a virtual face image from which the mask is removed by using the first neural network model (S130). At this time, techniques such as generative adversarial networks (GAN), Unpaired Image-to-Image Translation, Variational Autoencoder (VAE), and Deepfake may be used as the neural network model used. For example, the computing device 100 may input information on the identified mask-wearing face image to a neural network model to convert the mask-wearing portion into a virtual face image, and obtain a virtual face image from which the mask is removed.

In addition, the computing device 100 uses a second neural network model to convert the mask-removed virtual face image obtained through step S130 into a face image of a related person without a mask worn through step S120 (that is, , “face image conversion technology”) may be applied (S140). The computing device 100 can effectively obtain an image of a restoration target with the mask removed by synthesizing "the associated person's mask-less image" with the "virtual face image" in step S140. In this case, the first neural network model and the second neural network model may be configured separately or configured as a single neural network according to an embodiment. In addition, technologies such as Conditional Generative Adversarial Networks (cGAN), Unpaired Image-to-Image Translation, and Conditional Variational Autoencoder (cVAE) can be used in the process of synthesizing the unmasked image of the related person. In addition, in the synthesis process, GAN Inversion technology can be used to transform specific attributes in latent space. The computing device 100 may obtain the following technical effects by adding a process of acquiring a virtual face image from which the mask is removed by using a neural network model before applying the face image conversion technology. Specifically, in the process of generating a picture of an area covered by an existing mask, it is difficult to restore the same person and it is possible to solve the problem that image conversion cannot be performed effectively.

The computing device 100 does not directly apply the face image conversion technology to the mask-wearing face image, but converts the mask-wearing face image into a virtual face image (serving as an intermediate medium) and then applies the face image conversion technology to the following Such technical effects can be obtained. Specifically, it is possible to solve “the problem of the prior art that it is difficult to directly apply the face image conversion technology and the quality is low because the masking face image is not a substantially complete face shape”.

According to an embodiment of the present disclosure, information for restoration may include a face image not wearing a mask. For example, the information for restoration may include “a mask-free face image of each person included in the image to be restored”. In addition, the face image of each person not wearing a mask may include an image provided by a user or manually or automatically provided from a photo album.

The processor 110 may identify a “mask-wearing face image included in a restoration target image” to restore a mask-wearing face image, and may obtain a “mask-wearing face image of a person related to the identified mask-wearing face image”. . In addition, the identified mask-wearing face image may be converted into a virtual face image from which the mask is removed by using the first neural network model. Additionally, an operation of applying a face image conversion technique from “the virtual face image from which the mask is removed” to the “obtained face image without a mask worn” may be included using a second neural network model. In this case, the first neural network model and the second neural network model may be configured separately or configured as a single neural network according to an embodiment. In addition, the processor 110 may convert the identified mask-wearing face image into a virtual face image from which the mask is removed by using a generation model of Generative Adversarial Networks (GAN). Specifically, referring to FIG. 4 , the processor 110 may identify “a mask-wearing face image 11 included in a restoration target image” to restore a mask-wearing face image. In addition, the processor 110 A “face image 12 of a person not wearing a mask associated with the identified face image wearing a mask” may be acquired. At this time, in the process of acquiring the “face image of a person without a mask wearing a mask associated with the face image wearing a mask”, the similarity between “the face image without a mask provided in advance” and the “face area other than wearing a mask included in the image to be restored” is analyzed. Thus, a process of searching for and obtaining a face image of the associated person not wearing a mask may be included.

Additionally, the processor 110 may convert the identified mask-wearing face image 11 into a virtual face image 31 from which the mask is removed by using the first neural network model (21). At this time, techniques such as generative adversarial networks (GAN), Unpaired Image-to-Image Translation, Variational Autoencoder (VAE), and Deepfake may be used as the neural network model used. For example, the processor 110 inputs information of the identified mask-wearing face image 11 to a first neural network model to convert the mask-wearing portion into a virtual face image (21), and the virtual face image from which the mask is removed ( 31) can be obtained.

In addition, the processor 110 converts the “virtual face image 31 with the mask removed obtained through step 21” into the “mask-unwearing face image 12 of the associated person” by utilizing the second neural network model. technology (ie, “face image conversion technology”)” can be applied (41). The processor 110 may synthesize the mask-unwearing image 12 of the related person to the virtual face image 31 through the application step (step 41) of face image conversion technology using a neural network model. Through this, the processor 110 may obtain an image 51 of a state in which the mask of the restoration target is removed. In this case, the first neural network model and the second neural network model may be configured separately or configured as a single neural network according to an embodiment. In addition, facial image conversion technology using a neural network model may include artificial intelligence-based image synthesis technologies such as deep fake, face 2 face, face swap, neural textures, and pristine. In addition, in the process of synthesizing "unmasked images of related persons", technologies such as Conditional Generative Adversarial Networks (cGAN), Unpaired Image-to-Image Translation, and Conditional Variational Autoencoder (cVAE) can be used. Transformation of a specific attribute in latent space can also be utilized. A face image conversion technology using a neural network model may include the information of the above-described example, but is not limited to the above-described example and is within the range that a person skilled in the art can understand. can be configured in a variety of ways.

5 is a flowchart illustrating a process of partially synthesizing a face image using a face image conversion technique using a neural network model according to an embodiment of the present disclosure.

Referring to FIG. 5 , the computing device 100 according to an embodiment of the present disclosure may obtain restoration target image information from internal storage or receive restoration target image information from an external system (S210). The external system may be a server, database, or the like that stores and manages information for restoring an image of a face wearing a mask. The computing device 100 may use information received from an external system as input data for restoring a facial image of a mask wearing portion. The use pattern of such information may vary according to the purpose of restoring the face image of the mask wearing part.

In addition, the computing device 100 may identify a mask-wearing face image included in the received restoration target image, and identify a partial region including a mask-wearing face image within the restoration target image (S220).

In addition, the computing device 100 may obtain a face image of a person not wearing a mask associated with the identified face image wearing a mask by using the face image wearing a mask identified through step S220 (S230).

In addition, the computing device 100 partially applies face image conversion technology to the acquired face image of the mask-wearing partial region based on the face image of the associated person without a mask, obtained through step S230, by utilizing the neural network model. (For example, partial synthesis is performed on a mask-wearing area of the face area, and the area other than the mask-wearing area is used as it is without transformation) (S240). The computing device 100 may synthesize an image of a related person not wearing a mask with respect to the part recognized as the part wearing the mask through step S240. Through this, it is possible to obtain a similar image of a state in which the mask of the restoration target is removed. The computing device 100 obtains a face image from which the mask is removed by partially utilizing a face image conversion technology only in the mask wearing region, so that the mask of the photo to be restored (unlike the embodiments in which conversion is performed on the entire face region). It is possible to obtain a technical effect that can use the image of the part that is not covered by .

6 is a partial synthesis of a face image using a face image conversion technology using a neural network model according to an embodiment of the present disclosure (eg, partial synthesis is performed for a mask wearing region among face regions, and other than mask wearing). It is a schematic diagram for explaining how to use the area of ) as it is without conversion.

Referring to FIG. 6 , the processor 110 may identify a face image 61 wearing a mask included in a restoration target image, and may identify a mask wearing region of the identified image. In addition, the processor 110 may obtain the “face image 62 of a person not wearing a mask related to the identified face image 61 wearing a mask”. In addition, the processor 110 may extract a portion corresponding to the mask wearing region of the identified mask wearing face image 61 from the obtained mask-unwearing face image 62, and based on the extracted image, The partial image conversion technique 71 may be applied only to the mask wearing region of the identified mask wearing face image 61 . Meanwhile, since the processor 110 applies partial image conversion only to the mask wearing area, the remaining areas of the identified mask wearing face image 61 excluding the mask wearing area may be utilized as they are.

Meanwhile, the partial image conversion may be implemented by various technologies including face image conversion technology using a neural network model. In addition, the facial image conversion technology using the neural network model may include artificial intelligence-based image synthesis technologies such as deep fake, face 2 face, face swap, neural textures, and pristine. In addition, in the process of synthesizing an unmasked image of a related person, technologies such as Conditional Generative Adversarial Networks (cGAN), Unpaired Image-to-Image Translation, and Conditional Variational Autoencoder (cVAE) can be used. It can also be utilized to transform specific properties in . Facial image conversion technology using a neural network model may include the information of the above-described example, but is not limited to the above-described example and may be configured in various ways within a range that a person skilled in the art can understand.

Referring to FIG. 7 , FIG. 7 is a schematic diagram illustrating a method of synthesizing a plurality of face images using a face image conversion technique using a neural network model according to an embodiment of the present disclosure.

Specifically, when the processor 110 identifies a mask-wearing face image included in the restoration target image 91, a plurality of mask-wearing faces included in the restoration target image 91 Images can be identified (92). Also, the processor 110 may obtain a plurality of mask-unwearing face images 93 of a plurality of people associated with the plurality of mask-wearing face images. At this time, the process of obtaining face images of a plurality of related persons without a mask is analyzed by analyzing the degree of similarity between the “face photograph of the face without a mask provided in advance” and the “face area other than wearing a mask in the image to be restored”, It may include a process of searching for and obtaining a face image without a mask. Additionally, when synthesizing the acquired mask-wearing face image with the identified mask-wearing face image, the “acquired plurality of mask-wearing face images, respectively” is added to the “identified plurality of mask-wearing face images, respectively.” can be synthesized. (94)

The processor 110 may acquire “an image 95 of a state in which masks of each of a plurality of restoration objects have been removed” through step 94 above.

At this time, according to an embodiment of the present disclosure, when the processor 110 synthesizes the “each of the plurality of acquired face images not wearing a mask” with the “each of the plurality of identified face images wearing a mask”, the first neural network Using the model, the identified plurality of mask-wearing face images may be converted into a plurality of virtual face images from which masks are removed. Also, by using the second neural network model, “each of the plurality of virtual face images from which the mask is removed” may be converted into the “each of the plurality of acquired face images not wearing the mask”. In this case, the first neural network model and the second neural network model may be configured separately or configured as a single neural network according to an embodiment. In addition, in the process of synthesizing unmasked images of each of a plurality of related persons, technologies such as Conditional Generative Adversarial Networks (cGAN), Unpaired Image-to-Image Translation, and Conditional Variational Autoencoder (cVAE) can be used, and GAN Inversion technology It can also be utilized to transform certain properties in latent space with .

The processor 110 may obtain the following technical effects by adding a process of obtaining a virtual face image from which a mask is removed by using a neural network model before applying face image conversion technology. Specifically, it is possible to solve a problem in which an image cannot be effectively converted when a plurality of people are included or the face regions are not aligned.

According to an embodiment of the present disclosure, a computer readable medium storing a data structure is disclosed.

Data structure can refer to the organization, management, and storage of data that enables efficient access and modification of data. Data structure may refer to the organization of data to solve a specific problem (eg, data retrieval, data storage, data modification in the shortest time). A data structure may 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 may include a connection relationship between user-defined data elements. A physical relationship between data elements may include an actual relationship between data elements physically stored in a computer-readable storage medium (eg, a persistent storage device). The data structure may specifically include a set of data, a relationship between data, and a function or command applicable to the data. Through an effectively designed data structure, a computing device can perform calculations while using minimal resources of the computing device. Specifically, the computing device can increase the efficiency of operation, reading, insertion, deletion, comparison, exchange, and search through an effectively designed data structure.

The data structure can be divided into a linear data structure and a non-linear data structure according to the shape of the data structure. A linear data structure may be a structure in which only one data is connected after one data. Linear data structures may include lists, stacks, queues, and decks. A list may refer to a series of data sets in which order exists internally. The list may include a linked list. A linked list may be a data structure in which data are connected in such a way that each data is connected in a single line with a pointer. In a linked list, a pointer can contain information about connection to the next or previous data. A linked list can be expressed as a singly linked list, a doubly linked list, or a circular linked list depending on the form. A stack can be a data enumeration structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (eg, inserted or deleted) at only one end of the data structure. The data stored in the stack may be a LIFO-Last in First Out (Last in First Out) data structure. A queue is a data listing structure that allows limited access to data, and unlike a stack, it can be a data structure (FIFO-First in First Out) in which data stored later comes out later. A deck can be a data structure that can handle data from either end of the data structure.

The nonlinear data structure may be a structure in which a plurality of data are connected after one data. The non-linear data structure may include a graph data structure. A graph data structure can be defined as a vertex and an edge, and an edge can include a line connecting two different vertices. A graph data structure may include a tree data structure. The tree data structure may be a data structure in which one path connects two different vertices among a plurality of vertices included in the tree. That is, it may be a data structure that does not form a loop in a graph data structure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, a neural network is unified and described. The data structure may include a neural network. And the data structure including the neural network may be stored in 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 function associated with each node or layer of the neural network, and neural network It may include a loss function for learning of . A data structure including a neural network may include any of the components described above. That is, the data structure including the neural network includes 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 function associated with each node or layer of the neural network, and neural network. It may be configured to include all or any combination thereof, such as a loss function for learning of . In addition to the foregoing configurations, the data structure comprising the neural network may include any other information that determines the characteristics of the neural network. In addition, the data structure may include all types of data used or generated in the computational process of the neural network, but is not limited to the above. A computer readable medium may include a computer readable recording medium and/or a computer readable transmission medium. A neural network may consist 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 includes one or more nodes.

The data structure may include data input to the neural network. A data structure including data input to the neural network may be stored in a computer readable medium. Data input to the neural network may include training data input during a neural network learning process and/or input data input to a neural network that has been trained. Data input to the neural network may include pre-processed data and/or data subject to pre-processing. Pre-processing may include a data processing process for inputting data to a neural network. Accordingly, the data structure may include data subject to pre-processing and data generated by pre-processing. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, weights and parameters may be used in the same meaning.) Also, a data structure including weights of a neural network may be stored in a computer readable medium. A neural network may include a plurality of weights. The weight may be variable, and may be changed by a user or an algorithm in order to perform a function desired by the neural network. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. A data value output from an output node may be determined based on the weight. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

As a non-limiting example, the weights may include weights that are varied during neural network training and/or weights for which neural network training has been completed. The variable weight in the neural network learning process may include a weight at the time the learning cycle starts and/or a variable weight during the learning cycle. The weights for which neural network learning has been completed may include weights for which learning cycles have been completed. Accordingly, the data structure including the weights of the neural network may include a data structure including weights that are variable during the neural network learning process and/or weights for which neural network learning is completed. Therefore, it is assumed that the above-described weights and/or combinations of weights are included in the data structure including the weights of the neural network. The foregoing data structure is only an example, and the present disclosure is not limited thereto.

The data structure including the weights of the neural network may be stored in a computer readable storage medium (eg, a memory or a hard disk) after going through a serialization process. Serialization can be the process of converting a data structure into a form that can be stored on the same or another computing device and later reconstructed and used. A computing device may serialize data structures to transmit and receive data over a network. The data structure including the weights of the serialized neural network may be reconstructed on the same computing device or another computing device through deserialization. The data structure including the weights of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network is a data structure for increasing the efficiency of operation while minimizing the resource of the computing device (for example, B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree). The foregoing is only an example, and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of the neural network. Also, the data structure including the hyperparameters of the neural network may be stored in a computer readable medium. A hyperparameter may be a variable variable by a user. Hyperparameters include, for example, learning rate, cost function, number of learning cycle iterations, weight initialization (eg, setting the range of weight values to be targeted for weight initialization), hidden unit number (eg, the number of hidden layers and the number of nodes in the hidden layer). The foregoing data structure is only an example, and the present disclosure is not limited thereto.

8 is a simplified and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has been described above as being generally embodied by a computing device, those skilled in the art will understand that the present disclosure may be combined with computer-executable instructions and/or other program modules that may be executed on one or more computers and/or may be implemented in hardware and software. It will be appreciated that it can be implemented as a combination.

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those skilled in the art will understand that the methods of the present disclosure can be applied to 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 ( It will be appreciated that each of these may be implemented with other computer system configurations, including those that may be operative in connection with one or more associated devices.

The described embodiments of the present disclosure may 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.

Computers typically include a variety of computer readable media. Computer readable media can be any medium that can be accessed by a computer, including volatile and nonvolatile media, transitory and non-transitory media, removable and non-transitory media. Includes removable media. By way of example, and not limitation, computer readable media may include computer readable storage media and computer readable transmission media. Computer readable storage media are volatile and nonvolatile media, transitory and non-transitory, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. includes media Computer readable storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device or other magnetic storage device. device, or any other medium that can be accessed by a computer and used to store desired information.

A computer readable transmission medium typically 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. Including all information delivery media. The term modulated data signal means a signal that has one or more of its characteristics set or changed so as to encode information within 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, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer readable transmission media.

An exemplary environment 1100 implementing various aspects of the present disclosure is shown including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 couples system components, including but not limited to system memory 1106 , to processing unit 1104 . Processing unit 1104 may be any of a variety of commercially available processors. Dual processor and other multiprocessor architectures may also be used as the processing unit 1104.

System bus 1108 may be any of several types of bus structures that may additionally be interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. 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 is a basic set of information that helps transfer information between components within computer 1102, such as during startup. contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

The computer 1102 may also include an internal hard disk drive (HDD) 1114 (eg, EIDE, SATA) - the internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes—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., a CD-ROM) for reading disc 1122 or reading from or writing to other high capacity optical media such as DVDs). The hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 are connected to the system bus 1108 by a hard disk drive interface 1124, magnetic disk drive interface 1126, and optical drive interface 1128, respectively. ) can be connected to The interface 1124 for external drive implementation includes at least one or both of USB (Universal Serial Bus) and IEEE 1394 interface technologies.

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 computer 1102, drives and media correspond to storing any data in a suitable digital format. Although the description of computer readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art can use zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other tangible media readable by the computer, such as the like, may also be used in the exemplary operating environment and any such media may include computer executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored on the drive and RAM 1112, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. 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 a variety of commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 1102 through 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, IR remote control, joystick, game pad, stylus pen, touch screen, and the like. Although these and other input devices are often connected to the processing unit 1104 through an input device interface 1142 that is connected to the system bus 1108, a parallel port, IEEE 1394 serial port, game port, USB port, IR interface, may be connected by other interfaces such as the like.

A monitor 1144 or other type of display device is also connected to the system bus 1108 through an interface such as a video adapter 1146. In addition to the monitor 1144, computers typically include other peripheral output devices (not shown) such as speakers, printers, and the like.

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. Remote computer(s) 1148 may be a workstation, computing device computer, router, personal computer, handheld computer, microprocessor-based entertainment device, peer device, or other common network node, and generally includes It includes many or all of the components described for, but for simplicity, only 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 corporations and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to worldwide computer networks, such as the Internet.

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

Computer 1102 is any wireless device or entity that is deployed and operating in wireless communication, eg, printers, scanners, desktop and/or portable computers, portable data assistants (PDAs), communication satellites, wireless detectable tags associated with It operates to communicate with arbitrary equipment or places and telephones. This includes at least Wi-Fi and Bluetooth wireless technologies. Thus, the communication may be a predefined structure as in conventional networks or simply an ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) makes it possible to connect to the Internet without wires. Wi-Fi is a wireless technology, such as a cell phone, that allows such devices, eg, computers, to transmit and receive data both indoors and outdoors, i.e. anywhere within coverage of a base station. Wi-Fi networks use a radio technology 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, for example, at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or in products that include both bands (dual band) .

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

Those skilled in the art will understand that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein are electronic hardware, (for convenience) , may be implemented by various forms of program or design code (referred to herein 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 on the particular application and the design constraints imposed on the overall system. Skilled artisans 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.

Various embodiments presented herein may 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 magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flash memory devices (eg, EEPROM, cards, sticks, key drives, etc.), but are not limited thereto. Additionally, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of example approaches. Based upon design priorities, it is to be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of this disclosure. The accompanying method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the presented 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 apparent to those skilled in the art of this disclosure, and the general principles defined herein may be applied to other embodiments without departing from the scope of this disclosure. Thus, the present disclosure is not to be limited to the embodiments presented herein, but is to be interpreted in the widest scope consistent with the principles and novel features presented herein.

Claims (11)

A method for restoring an image of a face wearing a mask, performed by one or more processors of a computing device, comprising:
identifying a face image wearing a mask included in a restoration target image;
acquiring a face image of a person associated with the identified face image wearing a mask without wearing a mask; and
Synthesizing the obtained face image not wearing a mask with the identified face image wearing a mask
including,
method.
According to claim 1,
Synthesizing the obtained mask-free face image with the identified mask-wearing face image,
converting the identified mask-wearing face image into a virtual face image from which the mask is removed by using a first neural network model; and
applying a face image conversion technique from the virtual face image from which the mask is removed to the acquired face image without a mask, using a second neural network model;
including,
method.
According to claim 2,
Converting the identified mask-wearing face image into a virtual face image from which the mask is removed by using the first neural network model,
Converting the identified mask-wearing face image into a virtual face image from which the mask is removed by using a generative adversarial networks (GAN) model
including,
method.
According to claim 1,
Identifying a face image wearing a mask included in the restoration target image,
Classifying and identifying a partial region including the mask-wearing face image in the restoration target image
including,
method.
According to claim 1,
Synthesizing the obtained mask-free face image with the identified mask-wearing face image,
applying a face image conversion technique to the obtained face image without a mask on a partial region including the identified face image wearing a mask in the restoration target image by using a neural network model;
including,
method.
According to claim 1,
Identifying a face image wearing a mask included in the restoration target image,
Including identifying a plurality of mask-wearing face images included in the restoration target image,
method.
According to claim 6,
Obtaining a mask-unwearing face image of a person associated with the identified mask-wearing face image,
Acquiring a plurality of mask-unwearing face images for a plurality of people associated with the plurality of mask-wearing face images,
method.
According to claim 7,
Synthesizing the obtained mask-free face image with the identified mask-wearing face image,
Comprising the step of combining each of the obtained plurality of face images without wearing a mask with each of the plurality of identified face images wearing a mask,
method.
According to claim 8,
The step of synthesizing each of the obtained plurality of face images not wearing a mask with each of the plurality of identified face images wearing a mask,
converting the identified plurality of mask-wearing face images into a plurality of mask-removed virtual face images using a first neural network model; and
Applying a face image conversion technique to each of the plurality of virtual face images from which the mask is removed to each of the plurality of obtained face images without wearing a mask, using a second neural network model;
including,
method.
A computer program stored on a computer-readable storage medium, which, when executed by one or more processors, causes the one or more processors to perform operations for restoring an image of a face wearing a mask, the operations comprising:
identifying an image of a face wearing a mask included in a restoration target image;
acquiring a face image of a person associated with the identified face image wearing a mask without wearing a mask; and
Synthesizing the obtained face image not wearing a mask with the identified face image wearing a mask
including,
A computer program stored on a computer readable storage medium.
As a computing device,
at least one processor; and
Memory
including,
The at least one processor,
identifying a face image wearing a mask included in a restoration target image;
obtaining a face image of a person associated with the identified face image wearing a mask without wearing a mask; and
Is configured to synthesize the obtained mask-free face image to the identified mask-wearing face image,
computing device.

Images