KR102517968B1 - Method for image feature ectraction by using neural network model - Google Patents

Abstract

According to an embodiment of the present disclosure, disclosed is a method for training a neural network model for extracting features of an image, which is performed by one or more processors of a computing device. The method includes the steps of: extracting a plurality of first feature vectors based on original image information; obtaining modified image information based on the original image information; extracting a plurality of second feature vectors based on the modified image information; calculating one or more weights based on the plurality of first feature vectors and the plurality of second feature vectors; calculating a loss function based on at least one of the one or more weights, the plurality of first feature vectors, or the plurality of second feature vectors; and learning a neural network model based on the loss function. The method allows the extraction of desired features from images by using the neural network model.

Description

Image feature extraction method using neural network model {METHOD FOR IMAGE FEATURE ECTRACTION BY USING NEURAL NETWORK MODEL}

The present disclosure relates to a method of using a neural network model to extract features of an image, and more particularly, to a method of extracting desired features from an image using a neural network model.

In the case of the existing face identification (Face Verification, Face Recognition) model, a method of simply extracting the face and learning other information unrelated to ID (identity) information was used, and the face angle, background, light, etc. There was a problem that ID information was extracted with little or no information related to ID information (Face Identity), and the ID information appeared differently depending on conditions. For this reason, in performing face-related tasks (task, for example, FaceSwap, Style Transfer, etc.), problems of deteriorating model performance occurred, and there were also problems following limitations in utilizing and developing the task. .

Therefore, there is a need for a method for reducing or removing the effect of the angle or background of the face during the process of extracting face ID information.

On the other hand, the present disclosure has been derived at least based on the technical background salpin above, but the technical problem or object of the present disclosure is not limited to solving the above salpin problems or disadvantages. That is, the present disclosure may cover various technical issues related to the content to be described below, in addition to the technical issues discussed above.

An object of the present disclosure is to provide a method for extracting desired features from an image using a neural network model.

On the other hand, the technical problem to be achieved by the present disclosure is not limited to the above-mentioned technical problem, and may include various technical problems within a range apparent to those skilled in the art from the contents to be described below.

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 extracting a plurality of first feature vectors based on original image information; obtaining modified image information based on the original image information; extracting a plurality of second feature vectors based on the transformed image information; calculating one or more weights based on the plurality of first feature vectors and the plurality of second feature vectors; calculating a loss function based on at least one of the one or more weights, the plurality of first feature vectors, or the plurality of second feature vectors; and training a neural network model based on the loss function.

Alternatively, obtaining transformed image information based on the original image information may include adding at least one of environment information, pose information, or hair information to the original image information. It may include obtaining transformed image information by applying.

Alternatively, extracting a plurality of first feature vectors based on the original image information may include extracting a plurality of first feature vectors by inputting the original image information to a plurality of identity (ID) extraction models, respectively. The step of extracting a plurality of second feature vectors based on the transformed image information comprises: extracting a plurality of second feature vectors by inputting the transformed image information to the plurality of ID extraction models, respectively. can include

Alternatively, the plurality of ID extraction models may be different models.

Alternatively, calculating one or more weights based on the plurality of first feature vectors and the plurality of second feature vectors may include corresponding the plurality of first feature vectors and the plurality of second feature vectors, respectively. step; measuring a degree of similarity between the plurality of first feature vectors and the plurality of second feature vectors corresponding to each other; and calculating the one or more weights based on the measured similarity, wherein the similarity may include cosine similarity.

Alternatively, calculating a loss function based on the one or more weights, at least one of the plurality of first feature vectors or the plurality of second feature vectors may include: calculating a first loss function based on the plurality of first feature vectors; extracting a synthetic feature vector; extracting a second composite feature vector based on the plurality of second feature vectors and the one or more weights; and calculating a first loss function by comparing the first synthesized feature vector and the second synthesized feature vector, wherein the step of learning a neural network model based on the loss function is based on the first loss function. and learning the first neural network model by doing so.

Alternatively, extracting a first composite feature vector based on the plurality of first feature vectors comprises extracting a first composite feature vector by concatenating the plurality of first feature vectors; , The step of extracting a second synthesized feature vector based on the plurality of second feature vectors and the one or more weights comprises performing a weighted sum operation on the plurality of second feature vectors based on the one or more weights. It may include extracting a second synthesized feature vector by performing.

Alternatively, calculating a loss function based on at least one of the one or more weights, the plurality of first feature vectors or the plurality of second feature vectors comprises: the plurality of first feature vectors and the one or more weights extracting a third synthesized feature vector based on; extracting a third feature vector by inputting the original image information to a second neural network model; and calculating a second loss function by comparing the third feature vector and the third composite feature vector, wherein the learning of the neural network model based on the loss function comprises: The step of training the second neural network model may be included.

Alternatively, extracting a third synthesized feature vector based on the plurality of first feature vectors and the one or more weights may include performing a weighted sum operation on the plurality of first feature vectors based on the one or more weights. The step of calculating a second loss function by comparing the third feature vector and the third synthesized feature vector is set based on the third synthesized feature vector. and calculating the second loss function by measuring an error with the third feature vector.

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 extracting features of an image, the operations comprising: extracting a plurality of first feature vectors based on original image information; movement; obtaining modified image information based on the original image information; extracting a plurality of second feature vectors based on the transformed image information; calculating one or more weights based on the plurality of first feature vectors and the plurality of second feature vectors; calculating a loss function based on at least one of the one or more weights, the plurality of first feature vectors, or the plurality of second feature vectors; and training a neural network model based on the loss function.

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 extracts a plurality of first feature vectors based on original image information; obtaining transformed image information based on the original image information; extracting a plurality of second feature vectors based on the transformed image information; calculate one or more weights based on the plurality of first feature vectors and the plurality of second feature vectors; calculate a loss function based on at least one of the one or more weights, the plurality of first feature vectors, or the plurality of second feature vectors; And it can be configured to train a neural network model based on the loss function.

A method for extracting features of an image performed by a computing device according to an embodiment of the present disclosure for realizing the above object is disclosed. The method includes inputting original image information into a pretrained neural network model and extracting a first feature vector, wherein the pretrained neural network model utilizes a plurality of ID (identity) extraction models to extract the original image. It may correspond to a pre-learned model based on a plurality of feature vectors extracted based on information.

The present disclosure may provide a method using a neural network model to extract features of an image, and through this, a method for extracting desired features from an image using the neural network model.

1 is a block diagram of a computing device for extracting features of an image 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 method of learning a neural network model for extracting features of an image according to an embodiment of the present disclosure.
4 is a schematic diagram illustrating a step of extracting a plurality of first feature vectors and a plurality of second feature vectors according to an embodiment of the present disclosure.
5 is a schematic diagram illustrating steps of calculating one or more weights, extracting a first composite feature vector and a second composite feature vector, and calculating a first loss function according to an embodiment of the present disclosure.
6 is a schematic diagram illustrating steps of extracting a third feature vector and a third synthesized feature vector and calculating a second loss function according to an embodiment of the present disclosure.
7 is a flowchart illustrating a method of extracting a first feature vector by inputting original image information to a pretrained 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”.

Skilled artisans 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 in electronic hardware, computer software, or both. It should be recognized that it can be implemented with combinations of 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 extracting features of an image 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 may recognize original image information to extract features of an image, extract a plurality of first feature vectors based on the original image information, and based on the original image information Thus, it is possible to perform operations for obtaining deformed image information. In this case, the original image information may include image information for extracting a desired feature such as face photo information of a specific person. The original image information may include various types of information in addition to these examples.

According to an embodiment of the present disclosure, the processor 110 may extract a plurality of second feature vectors based on the transformed image information, and the processor 110 may extract the plurality of first feature vectors and the plurality of second feature vectors. One or more weights may be calculated based on the second feature vector of . In addition, the processor 110 calculates a loss function based on at least one of the one or more weights, the plurality of first feature vectors, or the plurality of second feature vectors, and learns a neural network model based on the loss function. can be performed.

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 original image information from an external system. In this case, the information received from the database may be data for learning or inference for extracting features of an image using a neural network model. Original image information 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 extracting features of an image from an external database, generate an image feature extraction result, and provide a user interface related to the image feature extraction result to a user terminal. . At this time, the user terminal may output a user interface received from the computing device 100 as 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

3 is a flowchart illustrating a method of learning a neural network model for extracting features of an image according to an embodiment of the present disclosure.

The computing device 100 according to an embodiment of the present disclosure may directly acquire “original image information for extracting features of an image” or may receive it from an external system. Original image information is information that is a target for training a neural network model for extracting features of an image according to an embodiment of the present disclosure. The external system may be a server or database that stores and manages original image information. The computing device 100 may use original image information obtained directly or received from an external system as "input data for training a neural network model for extracting features of an image."

According to an embodiment of the present disclosure, the computing device 100 may extract a plurality of first feature vectors based on original image information (S110-1). For example, the computing device 100 may extract a plurality of first feature vectors by inputting original image information to a plurality of identity (ID) extraction models, respectively. In this case, each of the plurality of first feature vectors may include “feature information to be extracted from the original image information (eg, feature information capable of distinguishing a person's identity)”, and may include a plurality of IDs (identity information). ) Each extraction model may include a neural network model for extracting “feature information capable of distinguishing a person's identity” from an original image, and the plurality of ID extraction models may include different ID extraction models. there is. In addition, the model capable of extracting the first feature vector is not limited to an ID (identity) extraction model, and the “feature information to be extracted from the original image information” is “a feature capable of distinguishing a person's identity.” It is not limited to "information", and various information may be included in addition to these examples. A detailed process of extracting a plurality of first feature vectors based on original image information will be described later with reference to FIG. 4 .

The computing device 100 may acquire modified image information based on the original image information (S110-2). For example, the computing device 100 may obtain modified image information by applying at least one of environment information, pose information, and hair information to the original image information. . In this case, the environment information may include information such as background, clothes worn, lighting, and brightness, and the pose information may include information such as a face angle, gaze direction, and a person's facial expression, and the body hair information may include information such as hair, beard, and eyebrows. Meanwhile, the environment information, the pose information, or the hair information may include various pieces of information other than these examples. Also, the computing device 100 may extract a plurality of second feature vectors based on the transformed image information (S110-3). For example, the computing device 100 may extract the plurality of second feature vectors by inputting the transformed image information to the plurality of identity (ID) extraction models, respectively. At this time, each of the plurality of second feature vectors is “feature information to be extracted from the original image information” and “information other than feature information to be extracted from the original image information (eg, environment information, pose information, body hair information, etc.) )” may be included. In addition, each of the plurality of identity (ID) extraction models may include a neural network model for extracting "feature information capable of distinguishing a person's identity" from the transformed image information, and the plurality of first feature vectors It may include the same model as the model for extracting . Meanwhile, the model capable of extracting the second feature vector is not limited to an ID (identity) extraction model, and the “information other than the feature information to be extracted from the original image information” includes environment information, pose ) information or hair information, and various information other than these examples may be included. A detailed process of obtaining modified image information based on original image information and extracting a plurality of second feature vectors will be described later with reference to FIG. 4 .

The computing device 100 determines one or more weights based on “a plurality of first feature vectors obtained through steps S110-1” and “a plurality of second feature vectors obtained through steps S110-2 to S110-3”. It can be calculated (S120). For example, the computing device 100 maps the plurality of first feature vectors and the plurality of second feature vectors, respectively, and the similarity between the plurality of first feature vectors and the plurality of second feature vectors. may be measured, and the one or more weights may be calculated based on the measured similarity. In this case, the similarity may include cosine similarity, but may include various similarity measurement results in addition to cosine similarity. A detailed process of calculating one or more weights based on a plurality of first feature vectors and a plurality of second feature vectors will be described later with reference to FIG. 5 .

The computing device 100 may include "one or more weights calculated through step S120", "a plurality of first feature vectors obtained through step S110-1" or "a plurality of values obtained through steps S110-2 to S110-3". A loss function may be calculated based on at least one of “the second feature vector” (S130). For example, according to an embodiment of the present disclosure, the computing device 100 extracts a first synthesized feature vector based on the plurality of first feature vectors, and determines the plurality of second feature vectors and the one or more weights. Extracting a second synthetic feature vector based on the A first loss function may be calculated by comparing the first synthesized feature vector and the second synthesized feature vector. In addition, the computing device 100 may extract a first synthesized feature vector by concatenating a plurality of first feature vectors, and perform a weighted sum of the plurality of second feature vectors based on the one or more weights ( weighted sum) operation may be performed to extract the second composite feature vector. A detailed process of extracting the first synthesized feature vector and the second synthesized feature vector and calculating the first loss function will be described later with reference to FIG. 5 .

Meanwhile, according to another embodiment of the present disclosure, the computing device 100 extracts a third synthesized feature vector based on the plurality of first feature vectors and the one or more weights, and converts the original image information into a second neural network model. A third feature vector may be extracted by inputting the input, and a second loss function may be calculated by comparing the third feature vector and the third synthesized feature vector. In this case, the computing device 100 may extract a third synthesized feature vector by performing a weighted sum operation on the plurality of first feature vectors based on the one or more weights. In addition, the computing device 100 may calculate the second loss function by setting the third synthesized feature vector as a reference and measuring an error with the third feature vector. A detailed process of extracting the third feature vector and the third synthesized feature vector and calculating the second loss function will be described later with reference to FIG. 6 .

The computing device 100 may train a neural network model based on the loss function calculated through step S130 (S140). For example, the computing device 100 may train the first neural network model based on the first loss function, and may train the second neural network model based on the second loss function. In this case, the first neural network model and the second neural network model may be different from each other. In addition, the first neural network model or the second neural network model, which is a learning target, corresponds to one of the plurality of ID (identity) extraction models or a separate model different from the plurality of ID (identity) extraction models. can be a model of Through this learning process, when the neural network model extracts “feature information to be extracted from the original image information” from the original image information, the influence of “information other than the feature information to be extracted from the original image information” is reduced. direction can be learned. For example, since “the embedding result of the original image information” and “the embedding result of the image information in which information unrelated to the ID feature information is additionally modified” are similarly learned to each other, as a result, the ID feature information and A neural network model can be trained in such a way that the influence of irrelevant information is reduced.

Meanwhile, in the present disclosure, terms such as "first", "second", and "third" are used to distinguish one component from another component and maintain consistency throughout the specification, and these terms The scope of rights should not be limited by A detailed process of learning the neural network model based on the first and second loss functions calculated in step S130 will be described later with reference to FIGS. 5 and 6 .

4 is a schematic diagram illustrating a step of extracting a plurality of first feature vectors and a plurality of second feature vectors according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the computing device 100 may input the original image information 11 to the neural network model 12 to extract a plurality of first feature vectors 13 . For example, the neural network model 12 may include a plurality of ID (identity) extraction models, and the plurality of ID extraction models may be different ID extraction models, and various models other than these examples may be included. there is. Each of the plurality of first feature vectors 13 may include "feature information to be extracted from original image information (eg, feature information capable of distinguishing a person's identity)", and the plurality of The ID (identity) extraction model may include a neural network model for extracting "characteristic information capable of distinguishing a person's identity" from the original image information 11 . Also, the plurality of first feature vectors 13 may be extracted from a plurality of different ID extraction models. The “feature information to be extracted from the original image information” is not limited to “feature information capable of distinguishing a person's identity” and may include various types of information in addition to these examples.

In addition, the computing device 100 adds “information other than feature information to be extracted from the original image information (eg, environment information, pose information, body hair information, etc.)” to the original image information 11 (14-1). By applying (14), transformed image information (15) can be obtained. For example, after the original image information 11 is input to the encoder and encoded, the computing device 100 applies (adds) pose information and body hair information to the encoded information in a latent space. Transformed encoding information can be generated, and by performing a decoding process on the transformed encoding information using a decoder, the angle of the head is turned in the original image information 11, and beard and hair are added. Image information 15” can be obtained.

According to an embodiment of the present disclosure, the computing device 100 may extract the plurality of second feature vectors 16 by inputting the transformed image information 15 to the neural network model 12 . For example, the computing device 100 may extract the plurality of second feature vectors 16 by inputting the transformed image information 15 to a plurality of ID extraction models, respectively. In addition, each of the plurality of second feature vectors 16 may include “feature information to be extracted from original image information” and “information other than feature information to be extracted from original image information”. For example, “feature information to be extracted from original image information” is In the case of "feature information that can distinguish identity", the plurality of second feature vectors 16 are "information unnecessary for distinguishing the identity of a person (eg, face angle, position of lighting, presence or absence of hair, etc.)”. For example, the plurality of second feature vectors 16 may include feature vectors extracted by inputting information about a face angle, a position of lighting, and a deformed hair to a plurality of ID extraction models, respectively. Meanwhile, as an additional embodiment, the computing device 100 may generate the plurality of second feature vectors 16 by inputting different deformed images to the plurality of ID extraction models. In other words, the plurality of second feature vectors 16 include a plurality of first modified image information in which the angle of the face is modified, second modified image information in which the position of lighting is modified, and third modified image information in which the hair is modified. It may also include feature vectors extracted by being input to the ID extraction model. The process of calculating one or more weights based on the plurality of first feature vectors 13 and the plurality of second feature vectors 16, calculating a loss function based thereon, and learning a neural network model through the loss function It will be described in detail with reference to FIG. 5 below.

5 is a schematic diagram illustrating steps of calculating one or more weights, extracting a first composite feature vector and a second composite feature vector, and calculating a first loss function according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the computing device 100 may calculate one or more weights 22 based on the plurality of first feature vectors 13 and the plurality of second feature vectors 16 (21 ). In this case, the computing device 100 may correspond the plurality of first feature vectors 13 and the plurality of second feature vectors 16 to each other. For example, among the plurality of second feature vectors 16, a number 1 is given to a second feature vector extracted from a first ID (identity) extraction model, and a number extracted from the second and third ID extraction models, respectively. Numbers 2 and 3 may be assigned to the second feature vectors, respectively. In addition, the same process may be performed for each of the plurality of first feature vectors 13, and numbers 1, 2, and 3 may be assigned to each of the three first feature vectors, and the computing device 100 may assign The plurality of first feature vectors 13 and the plurality of second feature vectors 16 may correspond to each other by corresponding each of the feature vectors having the same number.

On the other hand, according to another embodiment, the letter a is given to the second feature vector output based on “image information transformed based on environment information”, and “image information transformed based on pose information”, “ Letters b and c may be assigned to each of the second feature vectors output based on “image information transformed based on body hair information”. In addition, letters a, b, and c may be assigned to three first feature vectors among the plurality of first feature vectors 13, and the computing device 100 corresponds to feature vectors having the same assigned letters. By doing so, the plurality of first feature vectors 13 and the plurality of second feature vectors 16 may correspond to each other.

Additionally, the computing device 100 may measure a similarity between the corresponding plurality of first feature vectors 13 and the plurality of second feature vectors 16, and based on the measured similarity, the one or more corresponding Weights 22 can be calculated. For example, the cosine similarity between the “(No. 1) second feature vector extracted from the first ID (identity) extraction model” and the “(No. 1) first feature vector” corresponding thereto is measured, and the measured result "similarity 1" can be measured as (0.3), and the measured "similarity 1 (=0.3)" can be calculated as "weight w1." It may also be performed on the (2nd) second feature vector extracted from the extraction model and the (3rd) second feature vector extracted from the third ID (identity) extraction model, respectively, and as a result of the execution, “similarity 2” and its corresponding “weight w2” can be calculated as (0.5), and “similarity 3” and its corresponding “weight w3” can be calculated as (0.7).

Meanwhile, according to another embodiment, the cosine between “(a) second feature vector” output based on the “image information transformed based on environment information” and “(a) first feature vector” corresponding thereto The similarity is measured, the measured result “similarity (a)” can be measured as (0.3), and the measured “similarity (a)(=0.3)” can be calculated as “weight w(a)” there is. In addition, this process results in “(b) second feature vector” and “(c) second feature vector” output based on “image information transformed based on pose information” and “image information transformed based on body hair information,” respectively. 2 feature vectors”, and as a result of the execution, “similarity (b)” and its corresponding “weight w (b)” are calculated as (0.5), and “similarity (c)” and its corresponding The “weight w(c)” that becomes can be calculated as (0.7).

Meanwhile, the degree of similarity between the corresponding plurality of first feature vectors 13 and the plurality of second feature vectors 16 is measured, and the weight 22 is calculated based on the measured degree of similarity. The weights of the first or second feature vectors 13 and 16 containing a lot of information other than the feature information to be extracted from the original image information may be calculated low, respectively, and the "feature information to be extracted from the original image information" The weights of the first or second feature vectors 13 and 16 containing a lot of may be calculated to be high. Through this, in the process of extracting the first feature vector 13 and the second feature vector 16, the degree of concentration on "feature information to be extracted from the original image information (eg, ID feature information)" is increased, and the environment (expression , hairstyle, facial angle, etc.) can be minimized/removed to robustly extract “feature information (eg, ID feature information) that you want to extract from original image information” there is.

According to an embodiment of the present disclosure, the computing device 100 may extract a first synthesized feature vector 24 by concatenating the plurality of first feature vectors 13 (23). Through the process of step 23, the plurality of first feature vectors 13 can be extracted as one vector. In addition, the computing device 100 extracts a second synthesized feature vector 26 by performing a weighted sum operation on the plurality of second feature vectors 16 based on the one or more weights 22 can (25). For example, when the one or more weights 22 are calculated as “weight w1 (=0.3)”, “weight w2 (=0.5)”, and “weight w3 (=0.7)”, the second synthetic feature vector 26 ) is the “(No. 1) second feature vector” * “weight w1 (= 0.3)”, the “(No. 2) second feature vector” * “weight w2 (= 0.5)”, and the “(No. 3) ) second feature vector” * “weight w3 (= 0.7)” can be extracted as a result of performing a sum operation. In another embodiment, the one or more weights 22 are "weight w(a)(=0.3)", "weight w(b)(=0.5)", "weight w(c)(=0.7)" When calculated as , the second composite feature vector 26 is the “(a) second feature vector” * “weight w (a) (= 0.3)”, the “(b) second feature vector” * “weight w (b) (= 0.5)” and “(c) second feature vector” * “weight w (c) (= 0.7)” can be extracted as a result of the sum operation.

Computing device 100 according to an embodiment of the present disclosure calculates a first loss function 27 by comparing the first composite feature vector 24 and the second composite feature vector 26, and the first The first neural network model 12 can be trained based on the loss function 27 . For example, the error of the first composite feature vector 24 and the second composite feature vector 26 is calculated as a first loss function 27, and based on the first loss function 27, the first 1 neural network model 12 can be learned. Through this, when the first neural network model 12 extracts "feature information to be extracted from the original image information" from the original image information 11, the "information other than the feature information to be extracted from the original image information" It can be learned in a direction in which the degree of influence is reduced. For example, “the embedding result of inputting the original image information 11 to the first neural network model 12” and “the image information 15 in which information not related to the ID characteristic information is additionally transformed” Since the embedding result of inputting to the first neural network model 12 is similar to each other, as a result, the neural network model 12 can be learned in a direction in which the influence of information unrelated to ID characteristic information is reduced. It works. A specific process of extracting a third feature vector and a third composite feature vector based on the one or more weights 22 and the plurality of first or second feature vectors 13 and 16, respectively, and calculating a second loss function It is explained through FIG. 6 below.

6 is a schematic diagram illustrating steps of extracting a third feature vector and a third synthesized feature vector and calculating a second loss function according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the computing device 100 may extract a third synthesized feature vector 32 based on the plurality of first feature vectors 13 and the one or more weights 22 (31 ). The process of calculating the one or more weights 22 may refer to the description of FIG. 5 as described in detail above. Specifically, the computing device 100 performs a weighted sum operation on the plurality of first feature vectors 13 based on the one or more weights 22 to obtain a third synthesized feature vector 32 can be extracted (31). For example, when the one or more weights 22 are calculated as “weight w1 (=0.3)”, “weight w2 (=0.5)”, and “weight w3 (=0.7)”, the third synthesized feature vector (26 ) is the “(No. 1) first feature vector” * “weight w1 (= 0.3)”, the “(No. 2) first feature vector” * “weight w2 (= 0.5)”, and the “(No. 3) ) can be extracted as a result of performing a sum operation between “first feature vector”*“weight w3 (=0.7)”. In another embodiment, the one or more weights 22 are "weight w(a)(=0.3)", "weight w(b)(=0.5)", "weight w(c)(=0.7)" When calculated as , the third composite feature vector 26 is the “(a) first feature vector” * “weight w (a) (= 0.3)”, the “(b) first feature vector” * “weight w (b) (= 0.5)” and “(c) first feature vector” * “weight w (c) (= 0.7)” can be extracted as a result of the sum operation.

However, the numbers that are the values of the one or more weights 22 are only examples, and the one or more weights 22 are not limited thereto and may be calculated with various values.

According to an embodiment of the present disclosure, the computing device 100 may extract the third feature vector 34 by inputting the original image information 11 to the second neural network model 33 . For example, the second neural network model 33 may include an ID (identity) extraction model, but may also include various other models. The third feature vector 34 may include “feature information to be extracted from original image information”.

According to an embodiment of the present disclosure, the computing device 100 may calculate the second loss function 35 by comparing the third feature vector 34 and the third synthesized feature vector 32 . For example, the computing device 100 sets the third synthetic feature vector 32 as a criterion, measures an error between the set criterion and the third feature vector 34, and calculates the second loss function 35. can be calculated Also, the computing device 100 may train the second neural network model 33 based on the second loss function 35 . Through this, the second neural network model 33 can be learned in a direction in which the error between the set reference and the third feature vector 34 is reduced, and the learned second neural network model 33 is dependent on external factors. By learning to minimize/remove the influence on the image, it is possible to better extract "feature information to be extracted from the original image information" from the original image information 11. In FIG. 7 , a process of extracting a first feature vector using a pretrained neural network model is described in detail.

7 is a flowchart illustrating a method of extracting a first feature vector by inputting original image information to a pretrained neural network model according to an embodiment of the present disclosure.

Referring to FIG. 7 , a neural network model is pre-trained based on a plurality of feature vectors extracted based on original image information 11 by utilizing a plurality of identity (ID) extraction models according to an embodiment of the present disclosure. It can (S210). Specifically, the original image information 11 or the transformed image information 15 is input to a plurality of ID (identity) extraction models, respectively, to obtain the plurality of first feature vectors 13 and the plurality of second feature vectors. (16), or the third feature vectors 34 may be extracted, respectively, and the extracted plurality of first feature vectors 13, the plurality of second feature vectors 16, or the third feature vector Based on at least one of (34), the neural network models 12 and 33 may be pre-trained. The detailed learning process may refer to the description of FIGS. 3 to 6 above.

According to an embodiment of the present disclosure, the original image information 11 may be input to the pretrained neural network models 12 and 33 to extract a first feature vector (S220). For example, a first feature vector including "feature information for identifying a person's identity" may be extracted from the original image information 11 . At this time, if the pre-learned neural network models (12, 33) are used, the influence of “information other than feature information (eg, environment, pose, body hair information, etc.) that can distinguish a person’s identity” is reduced. Feature vectors can be extracted.

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 with hardware. It will be appreciated that it can be implemented as a combination of software.

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, it will be appreciated by those skilled in the art that the methods of the present disclosure may be used in 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 other computer system configurations may be implemented, including (each of which 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.

A computer typically includes 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 removable diskettes 1118), and an optical disk drive 1120 (e.g., 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 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. 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, and cartridges. It will be appreciated that other tangible computer readable media such as , , and the like may also be used in the exemplary operating environment and that 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 (12)

A method of learning a neural network model for extracting features of an image, performed by a computing device, comprising:
extracting a plurality of first feature vectors based on original image information;
obtaining modified image information based on the original image information;
extracting a plurality of second feature vectors based on the transformed image information;
calculating one or more weights based on the plurality of first feature vectors and the plurality of second feature vectors;
extracting a first synthesized feature vector based on the plurality of first feature vectors;
extracting a second composite feature vector based on the plurality of second feature vectors and the one or more weights;
calculating a first loss function by comparing the first synthesized feature vector and the second synthesized feature vector; and
training a first neural network model based on the first loss function;
including,
method.
According to claim 1,
Obtaining transformed image information based on the original image information,
obtaining modified image information by applying at least one of environment information, pose information, and hair information to the original image information;
including,
method.
According to claim 1,
The step of extracting a plurality of first feature vectors based on the original image information,
Extracting a plurality of first feature vectors by inputting original image information into a plurality of identity (ID) extraction models, respectively;
Extracting a plurality of second feature vectors based on the transformed image information includes:
Extracting a plurality of second feature vectors by inputting the transformed image information into the plurality of ID extraction models, respectively.
method.
According to claim 3,
The plurality of ID extraction models are different models,
method.
According to claim 1,
Calculating one or more weights based on the plurality of first feature vectors and the plurality of second feature vectors,
correlating the plurality of first feature vectors and the plurality of second feature vectors, respectively;
measuring a degree of similarity between the plurality of first feature vectors and the plurality of second feature vectors corresponding to each other; and
calculating the one or more weights based on the measured similarity;
The similarity includes cosine similarity,
method.
delete According to claim 1,
The step of extracting a first synthesized feature vector based on the plurality of first feature vectors,
Extracting a first synthesized feature vector by concatenating the plurality of first feature vectors;
Extracting a second synthesized feature vector based on the plurality of second feature vectors and the one or more weights,
Extracting a second synthesized feature vector by performing a weighted sum operation on the plurality of second feature vectors based on the one or more weights,
method.
delete delete 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 extracting features of an image, the operations comprising:
extracting a plurality of first feature vectors based on original image information;
obtaining modified image information based on the original image information;
extracting a plurality of second feature vectors based on the transformed image information;
calculating one or more weights based on the plurality of first feature vectors and the plurality of second feature vectors;
extracting a first synthesized feature vector based on the plurality of first feature vectors;
extracting a second synthesized feature vector based on the plurality of second feature vectors and the one or more weights;
calculating a first loss function by comparing the first synthesized feature vector and the second synthesized feature vector; and
learning a first neural network model based on the first loss function;
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,
extracting a plurality of first feature vectors based on original image information;
obtaining transformed image information based on the original image information;
extracting a plurality of second feature vectors based on the transformed image information;
calculate one or more weights based on the plurality of first feature vectors and the plurality of second feature vectors;
extracting a first composite feature vector based on the plurality of first feature vectors;
extract a second composite feature vector based on the plurality of second feature vectors and the one or more weights;
calculate a first loss function by comparing the first composite feature vector and the second composite feature vector; and
configured to train a first neural network model based on the first loss function;
computing device.
A method of extracting features of an image, performed by a computing device, comprising:
Extracting a first feature vector by inputting original image information to a pretrained neural network model;
The pretrained neural network model,
A plurality of first feature vectors are extracted based on original image information using a plurality of identity (ID) extraction models, and a first synthesized feature vector extracted based on the plurality of first feature vectors;
a plurality of second feature vectors extracted based on the transformed image information;
one or more weights calculated based on the plurality of first feature vectors and the plurality of second feature vectors;
a second composite feature vector based on the plurality of second feature vectors and the one or more weights; and
Corresponding to a pretrained model based on a first loss function calculated by comparing the first synthesized feature vector and the second synthesized feature vector,
method.

Images