KR20240035302A - Method for restoring a masked face image by using the neural network model - Google Patents

Abstract

According to an embodiment of the present disclosure, a method of converting an image using a neural network model, performed by one or more processors of a computing device, is disclosed. The method includes extracting first partial image information based on first image information; extracting a latent vector of a first partial image based on the extracted first partial image information; and obtaining third image information by combining the extracted first partial image information with second image information based on the latent vector of the extracted first partial image.

Description

Partial image conversion method 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 partially modifying an image using a neural network model, and more specifically, to a technology for converting an image by partially compositing part of an image with another image using a neural network model.

In the case of the existing face swap model, it consists of a structure in which deep fake or face swap conversion is performed by receiving input of two images, the source face to be applied and the target face. However, there was a problem in that it was not possible to select and convert only the desired part (eyes, eyebrows, nose, mouth, face shape) of the face image to be applied. This was a problem that, regardless of the quality of the conversion model, could be a factor limiting the conversion diversity of results obtained by users who actually use the conversion model. Accordingly, the demand for technology that allows users to extract various results by partially selecting the area to be converted on the image is increasing.

Therefore, new technologies that can solve these problems are required.

The goal of the present disclosure is to provide a technology for modifying an image by partially compositing part of the image with another 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-described problem is disclosed. The method includes extracting first partial image information based on first image information; extracting a latent vector of the first partial image based on the extracted first partial image information; and

It may include obtaining third image information by combining the extracted first partial image information with second image information based on the latent vector of the extracted first partial image.

Alternatively, extracting first partial image information based on the first image information may include extracting first segmentation information for the first image information; Receiving condition information for the extracted first division information; and extracting the first partial image information based on the condition information and the extracted first division information.

Alternatively, extracting the first partial image information based on the condition information and the extracted first division information may include generating a masking area based on the condition information and the extracted first division information. ; and extracting the first partial image information using the masking area created for the first image information.

Alternatively, the step of obtaining third image information by combining the extracted first partial image information with second image information based on the latent vector of the extracted first partial image may include combining the second image information with a neural network. performing encoding by inputting it into the model; It may include obtaining the third image information by inputting the encoded second image information and the latent vector of the first partial image through conditional normalization.

Alternatively, the neural network model may include extracting second segmentation information for the second image information and extracting third segmentation information for the third image information; extracting first inverted partial image information based on inversion condition information contrasted with the condition information and the extracted second division information; extracting second inverted partial image information based on the inversion condition information and the extracted third division information; extracting a latent vector of a first inverted partial image based on the extracted first inverted partial image information, and extracting a latent vector of a second inverted partial image based on the extracted second inverted partial image information; Comparing a latent vector of the first inverted partial image with a latent vector of the extracted second inverted partial image to calculate a first error; and training the neural network model based on the calculated first error.

Alternatively, the neural network model may include extracting second partial image information based on the condition information and the extracted third segmentation information; extracting a latent vector of a second partial image based on the extracted second partial image information; Comparing a latent vector of the first partial image with a latent vector of the extracted second partial image to calculate a second error; And it may be a neural network model learned based on the step of training the neural network model based on the calculated second error.

Alternatively, the step of extracting first inversion partial image information based on the inversion condition information contrasted with the condition information and the extracted second division information is based on the inversion condition information and the extracted second division information. generating a first inverted masking area, and extracting the first inverted partial image information using the generated first inverted masking area for the second image information, and comparing it with the condition information. The step of extracting second inverted partial image information based on the inversion condition information and the extracted third division information generates a second inverted masking area based on the inversion condition information and the extracted third division information. and extracting the second inverted partial image information using the generated second inverted masking area for the third image information.

According to an embodiment of the present disclosure for realizing the above-described object, a computer program stored in a computer-readable storage medium is disclosed. When executed on one or more processors, the computer program causes the one or more processors to perform operations for converting an image using a neural network model, the operations comprising: converting first partial image information based on first image information; The operation of extracting; extracting a latent vector of a first partial image based on the extracted first partial image information; and obtaining third image information by combining the extracted first partial image information with second image information based on the latent vector of the extracted first partial image.

A computing device according to an embodiment of the present disclosure for realizing the above-described problem is disclosed. The device includes at least one processor; and a memory, wherein the processor extracts first partial image information based on the first image information; extracting a latent vector of the first partial image based on the extracted first partial image information; And, based on the latent vector of the extracted first partial image, the extracted first partial image information may be combined with the second image information to obtain third image information.

The present disclosure may provide a technology for converting an image by partially compositing part of the image with another image using a neural network model.

1 is a block diagram of a computing device for converting an image using a neural network model according to an embodiment of the present disclosure.
Figure 2 is a schematic diagram showing a network function according to an embodiment of the present disclosure.
Figure 3 is a flowchart illustrating a method of converting an image using a neural network model according to an embodiment of the present disclosure.
Figure 4 is a schematic diagram showing a process for extracting first partial image information according to an embodiment of the present disclosure.
Figure 5 is a schematic diagram illustrating a process of partially converting an image using a neural network model according to an embodiment of the present disclosure.
Figure 6 is a schematic diagram illustrating a process of learning a neural network model by comparing latent vectors of the first and second inverted partial images according to an embodiment of the present disclosure.
FIG. 7 is a schematic diagram illustrating a process of learning a neural network model by comparing latent vectors of first and second partial images according to an embodiment of the present disclosure.
Figure 8 is a brief, general schematic diagram of an example 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 disclosure. However, it is clear that these embodiments may be practiced without these specific descriptions.

As used herein, the terms “component,” “module,” “system,” and the like refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an implementation of software. For example, a component may be, but is not limited to, a process 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 can be a component. One or more components may reside within a processor and/or thread of execution. A component may be localized within one computer. A component may be distributed between two or more computers. Additionally, these components can execute from various computer-readable media having various data structures stored thereon. Components can transmit signals, for example, with one or more data packets (e.g., data and/or signals from one component interacting with other components in a local system, a distributed system, to other systems and over a network such as the Internet). Depending on the data being transmitted, they may communicate through local and/or remote processes.

Additionally, the term “or” is intended to mean an inclusive “or” and not an exclusive “or.” That is, unless otherwise specified or clear from context, “X utilizes A or B” is intended to mean one of the natural implicit substitutions. That is, either X uses A; X uses B; Or, if X uses both A and B, “X uses A or B” can apply to either of these cases. Additionally, the term “and/or” as used herein should be understood to refer to and include all possible combinations of one or more of the related listed items.

Additionally, the terms “comprise” and/or “comprising” should be understood to mean that the corresponding feature and/or element is present. However, the terms “comprise” and/or “comprising” should be understood as not excluding the presence or addition of one or more other features, elements and/or groups thereof. Additionally, unless otherwise specified or the context is clear to indicate a singular form, the singular terms herein and in the claims should generally be construed to mean “one or more.”

And, the term “at least one of A or B” should be interpreted to mean “a case containing only A,” “a case containing only B,” and “a case of combining A and B.”

Those skilled in the art will additionally recognize that the various illustrative logical blocks, components, modules, circuits, means, logic, and algorithm steps described in connection with the embodiments disclosed herein may be implemented using electronic hardware, computer software, or a combination of both. It must be recognized that it can be implemented with 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 software will depend on the specific application and design constraints imposed on the overall system. A skilled technician can implement the described functionality in a variety of ways for each specific application. However, such implementation decisions should not be construed as causing a departure from the scope of the present disclosure.

The description of the presented embodiments is provided to enable anyone 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. The general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Therefore, the present invention is not limited to the embodiments presented herein. The present invention is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

In this disclosure, network function, artificial neural network, and neural network may be used interchangeably.

1 is a block diagram of a computing device for converting an image 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 different components for performing the computing environment of the computing device 100, and only some of the disclosed components may configure 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 be composed of one or more cores, and may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit) may include a processor for data analysis and deep learning. 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 an operation for learning a neural network. The processor 110 is used for learning neural networks, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network 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, CPU and GPGPU can work together to process learning of network functions and data classification using network functions. Additionally, in one embodiment of the present disclosure, the processors of a plurality of computing devices can be used together to process learning of network functions and data classification using network functions. Additionally, 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 extracts first partial image information based on first image information to transform an image using a neural network model, and extracts first partial image information based on the extracted first partial image information. A latent vector of the first partial image can be extracted. At this time, the first image information may be information about an image with a characteristic (identity) desired to be input when converting an image. For example, if you want to input the features of eyes and nose in an image of a specific person when converting the image, the image information of the specific person may be included in the first image information.

According to an embodiment of the present disclosure, the processor 110 obtains third image information by combining the extracted first partial image information with second image information based on the latent vector of the extracted first partial image. can do. In addition, the processor 110 combines the first partial image information with the second image information to obtain third image information, allowing partial selection of the image area to be converted, thereby producing various image results reflecting the user's desired identity. It can be obtained.

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, hard disk type, multimedia card micro type, or card type memory (e.g. (e.g. SD or -Only Memory), and may include at least one type of storage medium among magnetic memory, magnetic disk, and optical disk. The computing device 100 may operate in connection with web storage that performs a storage function of the memory 130 on the Internet. The description of the memory described above is merely 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 first image information, second image information, or condition information from an external system. At this time, the information received from the database may be data for converting the image using a neural network model. The information of the first image may include the information of the above-described examples, but is not limited to the above-described examples and may be configured in various ways within a range understandable by those skilled in the art.

Additionally, the network unit 150 can transmit and receive information processed by the processor 110, a user interface, etc. through communication with other terminals. For example, the network unit 150 may provide a user interface generated by the processor 110 to a client (e.g. user terminal). Additionally, the network unit 150 may receive external input from a user authorized as a client and transmit it to the processor 110. At this time, the processor 110 may process operations such as output, modification, change, and addition 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 is a computing system that transmits and receives information through communication with a client and may include a server. At this time, the client may be any type of terminal that can access the server. For example, the computing device 100, which is a server, may receive information for converting an image using a neural network model from an external database, generate an image conversion result, and provide a user interface regarding the image conversion result to the user terminal. there is. At this time, the user terminal outputs the user interface received from the computing device 100, which is a server, and can input 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 an arbitrary server and performs additional information processing.

Figure 2 is a schematic diagram showing 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 can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node. Nodes (or neurons) that make up neural networks may be interconnected by one or more links.

Within a neural network, one or more nodes connected through a link may form a relative input node and output node relationship. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes 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 the data of the output node may be determined based on the data input to the input node. Here, the link connecting the input node and the output node may have a weight. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network can be determined according to the number of nodes and links within the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. For example, if the same number of nodes and links exist and two neural networks with different weight values of the links exist, the two neural networks may be recognized as different from each other.

A neural network may consist of a set of one or more nodes. A subset of nodes that make up a neural network can form a layer. Some of the nodes constituting the neural network may form one layer based on the distances from the first input node. For example, a set of nodes with a distance n from the initial input node may constitute n layers. The distance from the initial input node can be defined by the minimum number of links that must be passed to reach the node from the initial input node. However, this definition of a layer is arbitrary for explanation purposes, and the order of a layer within a neural network may be defined in a different way than described above. For example, a layer of nodes may be defined by distance from the final output node.

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

The neural network according to an embodiment of the present disclosure is a neural network in which 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 it progresses from the input layer to the hidden layer. You 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 in the input layer may be less than the number of nodes in the output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure may be 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 it progresses from the input layer to the hidden layer. You can. A neural network according to another embodiment of the present disclosure may be a neural network that is a combination of the above-described neural networks.

A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to the input layer and output layer. Deep neural networks allow you to identify latent structures in data. In other words, it is possible to identify the potential structure of a photo, text, video, voice, or music (e.g., what object is in the photo, what the content and emotion of the text are, what the content and emotion of the voice are, etc.) . Deep neural networks include convolutional neural networks (CNN), recurrent neural networks (RNN), auto encoders, generative adversarial networks (GAN), and restricted Boltzmann machines (RBM). machine), deep belief network (DBN), Q network, U network, Siamese network, Generative Adversarial Network (GAN), etc. 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 to output output data similar to input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be placed 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 the bottleneck layer (encoding), and then expanded symmetrically and reduced from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform nonlinear dimensionality reduction. The number of input layers and output layers can be corresponded to the dimension after preprocessing of the input data. In an auto-encoder structure, the number of nodes in the hidden layer included in the encoder may have a structure that decreases 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, not enough information may be conveyed, so if it is higher than a certain number (e.g., more than half of the input layers, etc.) ) may be maintained.

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

Neural networks can be trained to minimize output errors. In neural network learning, learning data is repeatedly input into the neural network, the output of the neural network and the error of the target for the learning data 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. This is the process of updating the weight of each node in the neural network through backpropagation. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (i.e., labeled learning data), and in the case of non-teacher learning, the correct answer may not be labeled in each learning data. That is, for example, in the case of teacher learning regarding data classification, the learning data may be data in which each learning data is labeled with a category. 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 label of the training data. As another example, in the case of non-teachable 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 reverse direction (i.e., from the output layer to the input layer) in the neural network, and the connection weight of each node in each layer of the neural network can be updated according to backpropagation. The amount of change in the connection weight of each updated node may be determined according to the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently depending on the number of repetitions of the learning cycle of the neural network. For example, in the early stages of neural network training, a high learning rate can be used to increase efficiency by allowing the neural network to quickly achieve a certain level of performance, and in the later stages of training, a low learning rate can be used to increase accuracy.

In the learning of neural networks, the training data can generally be a subset of real data (i.e., the data to be processed using the learned neural network), and thus the error for the training data is reduced, but the error for the real data is reduced. There may be an incremental learning cycle. Overfitting is a phenomenon in which errors in actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that learned a cat by showing a yellow cat fails to recognize that it is a cat when it sees a non-yellow cat may be a type of overfitting. Overfitting can cause errors in machine learning algorithms to increase. To prevent such overfitting, various optimization methods can be used. To prevent overfitting, methods such as increasing the learning data, regularization, dropout to disable some of the network nodes during the learning process, and use of a batch normalization layer can be applied. You can.

Reinforcement learning is a learning method that trains a neural network model based on the reward calculated for the 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 that indicate what the situation is at the current point in time, and can be understood as an input to a neural network model. Action refers to a decision based on the options that a neural network model can take, and can be understood as the output of a neural network model. Reward refers to the benefit that follows when a neural network model performs an action, and represents the value evaluated for the current state and action. Reinforcement learning can be understood as learning through trial and error in that rewards are given for actions. The reward given to the neural network model during the reinforcement learning process may be the cumulative reward of the results of multiple actions. Through reinforcement learning, it is possible to create a neural network model that maximizes the return, such as the reward itself or the total sum of the rewards, by considering rewards according to various states and actions.

Figure 3 is a flowchart illustrating a method of converting an image 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 directly obtain information for converting an image using a neural network model or receive it from an external system. The external system may be a server, database, etc. that stores and manages information for converting images using a neural network model. The computing device 100 may use first image information, second image information, condition information, etc. directly acquired or received from an external system as input data for converting an image using a neural network model.

The computing device 100 may extract first partial image information based on the first image information (S110). For example, the computing device 100 may extract first segmentation information for the first image information and receive condition information for the extracted first segmentation information, The first partial image information may be extracted based on the condition information and the extracted first division information. Additionally, the computing device 100 may generate a masking area based on the condition information and the extracted first division information, and use the generated masking area for the first image information to create the first partial image. Information can be extracted. The specific process for this is explained in detail in FIG. 4 below.

Additionally, the computing device 100 may extract a latent vector of the first partial image based on the first partial image information extracted through step S110 (S120). The specific process by which the latent vector of the image is extracted is explained in detail in FIG. 5 below.

Additionally, the computing device 100 may obtain third image information by combining the extracted first partial image information with the second image information based on the latent vector of the first partial image extracted through step S120 (S130) ). When obtaining third image information by combining the first partial image information with the second image information, a neural network model may be used. For example, the computing device 100 performs encoding by inputting the second image information into a neural network model, and performs conditional normalization on the encoded second image information and the latent vector of the first partial image. The third image information can be obtained by inputting the image information. The specific process for this is explained in Figure 5 below. Additionally, the computing device 100 may extract second division information for the second image information and third division information for the third image information. Thereafter, the computing device 100 may extract first inversion partial image information based on the inversion condition information and the extracted second division information compared with the condition information, and the inversion condition information and the extracted third division information. extracting second inverted partial image information based on the information, extracting a latent vector of the first inverted partial image based on the extracted first inverted partial image information, and extracting a latent vector of the first inverted partial image based on the extracted second inverted partial image information. The latent vector of the second inverted partial image can be extracted. Additionally, the computing device 100 calculates a first error by comparing the latent vector of the first inverted partial image with the latent vector of the extracted second inverted partial image, and operates the neural network based on the calculated first error. You can train a model.

Additionally, the computing device 100 extracts second partial image information based on the condition information and the extracted third division information, and generates a latent vector of the second partial image based on the extracted second partial image information. It can be extracted. Additionally, the computing device 100 calculates a second error by comparing the latent vector of the first partial image with the latent vector of the extracted second partial image, and creates the neural network model based on the calculated second error. Additional learning is possible. By learning the neural network model through the first error and the second error, when the neural network model performs image conversion, the characteristics of the partial image are more accurately applied to the part where condition information is input, and the condition information is not input. For parts that are not covered, a technical effect can be achieved in which the characteristics of the original image can be maintained. The specific learning process for the neural network model is described below with reference to FIGS. 6 and 7. By combining the partial image information of the first image with the second image through step S130, a partially converted image can be effectively obtained only for the desired features during image conversion. Additionally, 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 converting images. Additionally, in the image conversion process, GAN Inversion technology can be used to convert specific attributes in latent space.

Image conversion technology using a neural network model may include the information of the above-described examples, but is not limited to the above-described examples and may be configured in various ways within the range understandable by those skilled in the art. Among the embodiments of the present disclosure, an embodiment of extracting first partial image information will be described in detail with reference to FIG. 4 below.

Figure 4 is a schematic diagram showing a process for extracting first partial image information according to an embodiment of the present disclosure.

The computing device 100 according to an embodiment of the present disclosure extracts first segmentation information 12 for the first image using first image information 10 directly acquired or received from an external system. It can be done (11). At this time, the first image information may be information about an image whose identity you want to input when converting the image. For example, if you want to input the identity of the eyes, nose, mouth, etc. in the image of a specific person (a famous movie actor in the example in FIG. 4) when converting the image, the image information of the specific person whose identity is to be extracted is the first image information above. It may be included in the image information 10. In addition, deep learning-based segmentation technology can be used to extract the first segmentation information 12 for the first image information 10, and the deep learning-based segmentation technology used at this time is Fully Convolutional Network ( FCN), U-Net, DeepLab, Mask RCNN, etc. can be used.

The computing device 100 according to an embodiment of the present disclosure may receive condition information 13 for the extracted first division information 12. The condition information 13 refers to information that can be applied during image conversion among the first division information 12 for the first image information 10. For example, among the first segmentation information 12 for the first image information 10, the facial outlines of the eyes, nose, mouth, and lower canal can be input as the condition information 13 and applied when converting the image. At this time, the condition information 13 may be randomly assigned during learning, and may include information input from the user during inference. Meanwhile, by inputting the condition information 13, conversion can be performed by selecting the part to be converted from the image to be converted. In addition, the input condition information 13 can also be used when learning the “neural network model used for image conversion” described in FIGS. 6 and 7 below.

The computing device 100 according to an embodiment of the present disclosure may generate a masking area based on the condition information 13 and the extracted first division information 12, and the first image information 10 The first partial image information 15 can be extracted using the created masking area (14). For example, if the facial outlines of the eyes, nose, mouth, and lower duct are input as the condition information 13 among the first division information 12, the area excluding the facial outlines of the eyes, nose, mouth, and lower duct is masked. This applied masking area can be created. Then, first partial image information 15 can be extracted through element-wise product between the generated masking area and the first image information 10 (14). When extracting the first partial image information 15, various computational methods available to those skilled in the art may be utilized in addition to the element-wise product between the generated masking area and the first image information 10. The process of partially converting the image based on the extracted first partial image information 15 is explained in detail with reference to FIG. 5 below.

Figure 5 is a schematic diagram illustrating a process of partially converting an image using a neural network model according to an embodiment of the present disclosure.

The computing device 100 according to an embodiment of the present disclosure may extract the latent vector 21 of the first partial image based on the extracted first partial image information 15 (20). For example, the computing device 100 inputs the extracted first partial image information 15 into an ID embedding network (e.g., ArcFace, ShphereFace, etc.) to identify the eyes, nose, mouth, and lower abdomen that can be applied when converting the image. The latent vector 21 of the first partial image including features such as facial outline can be extracted.

The computing device 100 according to an embodiment of the present disclosure may perform encoding by inputting the second image information 22 into the neural network model 23. At this time, the second image information 22 may include an image with characteristics desired to be preserved when converting the image. For example, referring to FIG. 5, the second image information 22 includes posture, expression, texture, background, gaze direction, etc., excluding the facial outline features of the eyes, nose, mouth, and lower body that can be applied when converting the image. It may include an image of a person with . By performing encoding on the second image information 22, it is possible to perform an operation with the latent vector 21 of the first partial image when performing image transformation through the neural network model 23. Thereafter, the encoded second image information and the latent vector 21 of the first partial image can be input into the neural network model 23 through conditional normalization to obtain the third image information 24. The third image information 24 has the features of the first image information 10 to be applied when converting the image, and the features to be preserved when converting the image of the second image information 22 are preserved. Result images may be included. For example, referring to Figure 5, the facial contour features (15) of the eyes, nose, mouth, and lower crown of a famous movie star that you want to apply when converting the image are applied to the facial image (22) of an ordinary person to create a neural network model. Through this, it is possible to obtain “a facial image of an ordinary person (24) in which the facial contour features of the eyes, nose, mouth, and lower jaw of a famous movie star are applied, and the remaining features are maintained.” At this time, the neural network model 23 used for image conversion can utilize technologies such as the generative model of GAN (Generative Adversarial Networks), Unpaired Image-to-Image Translation, Variational Autoencoder (VAE), and Deepfake. GAN Inversion Technology can also be used to transform specific properties in latent space. Image conversion technology using a neural network model may include the information of the above-described examples, but is not limited to the above-described examples and may be configured in various ways within the range understandable by those skilled in the art. Additionally, in order to increase the accuracy of image conversion, learning may be performed on the neural network model 23, and the specific learning process for the neural network model 23 will be described with reference to FIGS. 6 and 7 below.

Figure 6 is a schematic diagram illustrating a process of learning a neural network model by comparing latent vectors of the first and second inverted partial images according to an embodiment of the present disclosure.

The computing device 100 according to an embodiment of the present disclosure extracts second division information 30 for the second image information 22 (11) and third information for the third image information 24. Segmentation information (31) can be extracted (11). Segmentation technology based on deep learning can be used to extract segmentation information (30, 31) for the second image information (22) and the third image information (24), and the deep learning-based Segmentation technologies such as Fully Convolutional Network (FCN), U-Net, DeepLab, and Mask RCNN can be used.

The computing device 100 according to an embodiment of the present disclosure may include inversion condition information 32 (e.g., information with features desired to be preserved when converting an image), which is contrasted with the input condition information 13. , Referring to FIG. 6, it may include “the remaining features excluding the features of the facial outline of the eyes, nose, mouth, and lower crown”) and the first inversion portion based on the extracted second segmentation information 30. Image information 34 may be extracted (33), and the computing device 100 may generate second inverted partial image information 35 based on the inversion condition information 32 and the extracted second division information 31. can be extracted (33). Specifically, the computing device 100 according to an embodiment of the present disclosure may generate a first inverted masking area based on the inversion condition information 32 and the extracted second division information 30, The first inverted partial image information 34 can be extracted using the first inverted masking area created for the second image information 22 (33). Additionally, the computing device 100 according to an embodiment of the present disclosure may generate a second inverted masking area based on the inversion condition information 32 and the extracted third division information 31, and The second inverted partial image information 35 can be extracted using the generated second inverted masking area for the third image information 24 (33). For example, when the facial outlines of the eyes, nose, mouth, and lower duct are input as the condition information 13 among the second and third division information 30, 31, the facial outlines of the eyes, nose, mouth, and lower duct are contrasted with this. First and second inverted masking areas in which masking is applied to the facial outline area may be created. In addition, the first inverted partial image information 34 can be extracted through an element-wise product between the generated first inverted masking area and the second image information 22, and the generated second inverted masking area The second inverted partial image information 35 can be extracted through element-wise product between and the third image information 24. When extracting the first and second inverted partial image information (34, 35), element-wise between the generated first or second inverted masking area and the second or third image information (22, 24) In addition to multiplication, various calculation methods available to those skilled in the art can be used.

In addition, the computing device 100 according to an embodiment of the present disclosure extracts a latent vector 36 of the first inverted partial image based on the extracted first inverted partial image information 34 (20), and Based on the extracted second inverted partial image information 35, the latent vector 37 of the second inverted partial image may be extracted (20). For example, the computing device 100 inputs the extracted first and second inverted partial image information 34 and 35 into an ID embedding network (e.g., ArcFace, ShphereFace, etc.) to determine the image information to be preserved when converting the image. , latent vectors (36, 37) of the first and second inverted partial images containing features excluding the facial outlines of the nose, mouth, and lower canal can be extracted.

In addition, the computing device 100 according to an embodiment of the present disclosure compares the latent vector 35 of the extracted first inverted partial image with the latent vector 35 of the extracted second inverted partial image to determine the first inverted partial image. The error can be calculated (38), and the neural network model (23) can be trained based on the calculated first error. For example, the first error can be calculated by performing a cosine similarity operation between the latent vector 35 of the extracted first inverted partial image and the latent vector 35 of the extracted second inverted partial image (38) , the neural network model 23 can be trained based on the first error by using the calculated first error as a loss term when learning the neural network model 23. In addition, by learning the neural network model 23 based on the first error, it is possible to obtain a technical effect that allows the features of the original image to be well maintained for the part that is desired to be preserved when converting the image. Additionally, the neural network model 23 can be additionally learned by comparing the latent vectors of the first and second partial images, and the specific process is described in FIG. 7 below.

FIG. 7 is a schematic diagram illustrating a process of learning a neural network model by comparing latent vectors of first and second partial images according to an embodiment of the present disclosure.

Referring to FIG. 7, the computing device 100 according to an embodiment of the present disclosure may extract third division information 31 for the third image information 24 (11). Deep learning-based segmentation technology can be used to extract segmentation information 31 for the third image information 24, and the deep learning-based segmentation technology used at this time is Fully Convolutional Network (FCN), U -Net, DeepLab, Mask RCNN, etc. can be used.

The computing device 100 according to an embodiment of the present disclosure may extract the second partial image information 40 based on the condition information 13 and the extracted third division information 31 (14). . The specific process of extracting the second partial image information 40 may be identical to the process of extracting the first partial image information 15.

Additionally, the computing device 100 according to an embodiment of the present disclosure may extract the latent vector 41 of the second partial image based on the extracted second partial image information 40 (20). For example, the computing device 100 inputs the extracted second partial image information 40 into an ID embedding network (e.g., ArcFace, ShphereFace, etc.) to select the eyes, nose, mouth, and lower abdomen to be applied when converting the image. The latent vector 41 of the second partial image containing the facial contour features of can be extracted.

Additionally, the computing device 100 according to an embodiment of the present disclosure compares the latent vector 21 of the extracted first partial image and the latent vector 41 of the extracted second partial image to calculate a second error. It can be calculated (42), and the neural network model (23) can be additionally trained based on the calculated second error. For example, the second error can be calculated by performing a cosine similarity operation between the latent vector 41 of the extracted second partial image and the latent vector 21 of the first partial image (42), and the calculated By using the second error as a loss term when learning the neural network model 23, the neural network model 23 can be additionally trained based on the second error. In addition, by additionally learning the neural network model 23 based on the second error, a technical effect can be obtained that allows the characteristics of the partial image to be applied more accurately when converting the image.

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 to enable efficient access and modification of data. Data structure can refer to the organization of data to solve a specific problem (e.g., retrieving data, storing data, or modifying data in the shortest possible time). A data structure may be defined as a physical or logical relationship between data elements designed to support a specific data processing function. Logical relationships between data elements may include connection relationships between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements that are physically stored in a computer-readable storage medium (e.g., a persistent storage device). A data structure may specifically include a set of data, relationships between data, and functions or instructions applicable to the data. Effectively designed data structures allow computing devices to perform computations while minimizing the use of the computing device's resources. Specifically, computing devices can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and search through effectively designed data structures.

Data structures can be divided into linear data structures and non-linear data structures depending on the type of data structure. A linear data structure may be a structure in which only one piece of data is connected to another piece of data. Linear data structures may include List, Stack, Queue, and Deque. A list can refer to a set of data that has an internal order. The list may include a linked list. A linked list may be a data structure in which data is connected in such a way that each data is connected in a single line with a pointer. In a linked list, a pointer may contain connection information to the next or previous data. Depending on its form, a linked list can be expressed as a singly linked list, a doubly linked list, or a circularly linked list. A stack may be a data listing structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (for example, inserted or deleted) at only one end of the data structure. Data stored in the stack may have a data structure (LIFO-Last in First Out) where the later it enters, the sooner it comes out. A queue is a data listing structure that allows limited access to data. Unlike the stack, it can be a data structure (FIFO-First in First Out) where data stored later is released later. A deck can be a data structure that can process data at both ends of the data structure.

A non-linear data structure may be a structure in which multiple pieces of data are connected behind one piece of data. Nonlinear data structures may 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 structure may include a tree data structure. A tree data structure may be a data structure in which there is only one path connecting two different vertices among a plurality of vertices included in the tree. In other words, it may be a data structure that does not form a loop in the graph data structure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Below, it is described in a unified manner as a neural network. Data structures may include neural networks. And the data structure including the neural network may be stored in a computer-readable medium. Data structures including neural networks also include data preprocessed for processing by a neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may include a loss function for learning. A data structure containing a neural network may include any of the components disclosed above. In other words, 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 acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may be configured to include all or any combination of the loss function for learning. In addition to the configurations described above, a data structure containing a neural network may include any other information that determines the characteristics of the neural network. Additionally, the data structure may include all types of data used or generated in the computational process of a neural network and is not limited to the above. Computer-readable media may include computer-readable recording media and/or computer-readable transmission media. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node.

The data structure may include data input to the neural network. A data structure containing data input to a neural network may be stored in a computer-readable medium. Data input to the neural network may include learning data input during the neural network learning process and/or input data input to the neural network on which training has been completed. Data input to the neural network may include data that has undergone pre-processing and/or data subject to pre-processing. Preprocessing may include a data processing process to input data into a neural network. Therefore, the data structure may include data subject to preprocessing and data generated by preprocessing. The above-described 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 with the same meaning.) And the data structure including the weights of the neural network may be stored in a computer-readable medium. A neural network may include multiple weights. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. Based on the weight, the data value output from the output node can be determined. The above-described data structure is only an example and the present disclosure is not limited thereto.

As an example and not a limitation, the weights may include weights that are changed during the neural network learning process and/or weights for which neural network learning has been completed. Weights that vary during the neural network learning process may include weights at the start of the learning cycle and/or weights that vary during the learning cycle. Weights for which neural network training has been completed may include weights for which a learning cycle has been completed. Therefore, a data structure including weights of a neural network may include weights that change during the neural network learning process and/or weights that have completed neural network learning. Therefore, the above-described weights and/or combinations of each weight are included in the data structure including the weights of the neural network. The above-described 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 (e.g., memory, 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 a different computing device and later reorganized and used. Computing devices can transmit and receive data over a network by serializing data structures. Data structures containing the weights of a serialized neural network can be reconstructed on the same computing device or on a different 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 to increase computational efficiency while minimizing the use of computing device resources (e.g., in non-linear data structures, B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree) may be included. The foregoing is merely an example and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of a neural network. And the data structure including the hyperparameters of the neural network can be stored in a computer-readable medium. A hyperparameter may be a variable that can be changed by the user. Hyperparameters include, for example, learning rate, cost function, number of learning cycle repetitions, weight initialization (e.g., setting the range of weight values subject to weight initialization), Hidden Unit. It may include a number (e.g., number of hidden layers, number of nodes in hidden layers). The above-described data structure is only an example and the present disclosure is not limited thereto.

Figure 8 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

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

Typically, program modules include routines, programs, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Additionally, those skilled in the art will understand that the methods of the present disclosure are applicable to single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. It will be appreciated that each of these may be implemented in other computer system configurations, including those capable of operating in conjunction with one or more associated devices.

The described embodiments of the 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.

Computers typically include a variety of computer-readable media. Computer-readable media can be any medium that can be accessed by a computer, and such computer-readable media includes volatile and non-volatile 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 refers to volatile and non-volatile media, transient and non-transitory media, removable and non-removable, 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, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage. This includes, but is not limited to, a device, or any other medium that can be accessed by a computer and used to store desired information.

A computer-readable transmission medium typically implements computer-readable instructions, data structures, program modules, or other data on a modulated data signal, such as a carrier wave or other transport mechanism. Includes all information delivery media. The term modulated data signal refers to a signal in which one or more of the characteristics of the signal have been set or changed 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 example environment 1100 is shown that implements various aspects of the present disclosure, 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 processors and other multiprocessor architectures may also be used as processing unit 1104.

System bus 1108 may be any of several types of bus structures that may further be interconnected to a memory bus, peripheral bus, and 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. The basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, and EEPROM, and is a basic input/output system that helps transfer information between components within the computer 1102, such as during startup. Contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

Computer 1102 may also include an internal hard disk drive (HDD) 1114 (e.g., 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 the disk 1122 or reading from or writing to other high-capacity optical media such as DVDs). Hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 are connected to system bus 1108 by hard disk drive interface 1124, magnetic disk drive interface 1126, and optical drive interface 1128, respectively. ) can be connected to. The interface 1124 for implementing an external drive includes at least one or both of Universal Serial Bus (USB) 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. For computer 1102, drive and media correspond to storing any data in a suitable digital format. Although the description of computer-readable media above refers to removable optical media such as HDDs, removable magnetic disks, and CDs or DVDs, those skilled in the art will also recognize removable optical media such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other types of computer-readable media, such as the like, may also be used in the example operating environment and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored in drives 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 on various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into computer 1102 through one or more wired/wireless input devices, such as a keyboard 1138 and a pointing device such as mouse 1140. Other input devices (not shown) may include microphones, IR remote controls, joysticks, game pads, stylus pens, touch screens, etc. These and other input devices are connected to the processing unit 1104 through an input device interface 1142, which is often connected to the system bus 1108, but may also include a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, It can be connected by other interfaces, etc.

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

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, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and is generally connected to computer 1102. For simplicity, only memory storage device 1150 is shown, although it includes many or all of the components described. The logical connections depicted include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, such as a wide area network (WAN) 1154. These LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a worldwide computer network, such as the Internet.

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

Computer 1102 may be associated with any wireless device or object deployed and operating in wireless communications, such as a printer, scanner, desktop and/or portable computer, portable data assistant (PDA), communications satellite, wirelessly detectable tag. Performs actions to communicate with any device or location and telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, communication may be a predefined structure as in a conventional network or may simply be ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) allows connection to the Internet, etc. without wires. Wi-Fi is a wireless technology, like cell phones, that allows these devices, such as computers, to send and receive data indoors and outdoors, anywhere within the coverage area of a base station. Wi-Fi networks use wireless 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, the Internet, and wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz wireless bands, for example, at data rates of 11 Mbps (802.11a) or 54 Mbps (802.11b), 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, commands, information, signals, bits, symbols and chips that may be referenced in the above description include voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields. It can be expressed by particles 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 may be used in electronic hardware, (for convenience) It will be understood that it 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 interoperability of hardware and software, various illustrative components, blocks, modules, circuits and steps have been described above generally with respect to their functionality. Whether this functionality is implemented as hardware or software depends on the specific application and design constraints imposed on the overall system. A person skilled in the art of this disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of this disclosure.

The 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 (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash. Includes, but is not limited to, memory devices (e.g., EEPROM, cards, sticks, key drives, etc.). 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 illustrative approaches. It is to be understood that the specific order or hierarchy of steps in processes may be rearranged within the scope of the present disclosure, based on design priorities. The appended method claims present elements of the various steps in a sample order but are not meant to be limited to the particular 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, and the general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Thus, the present disclosure is not limited to the embodiments presented herein but is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

Claims (1)

Methods and devices disclosed herein and in the drawings.