KR102608777B1 - Method, apparatus and computer program for providing automated calibration service for user's profile image - Google Patents

Abstract

A method, device, and computer program for providing an automated correction service for a user's profile image are provided. A method of providing an automated correction service for a user's profile image according to various embodiments of the present invention is a method performed by a computing device, comprising: acquiring an image including the user's face; analyzing the obtained image; It includes extracting features and performing correction on the user's face included in the image using the extracted features.

Description

Method, device, and computer program for providing automated correction service for user's profile image {METHOD, APPARATUS AND COMPUTER PROGRAM FOR PROVIDING AUTOMATED CALIBRATION SERVICE FOR USER'S PROFILE IMAGE}

Various embodiments of the present invention relate to a method, device, and computer program for providing an automated correction service for a user's profile image.

A profile photo is a photo taken to introduce and promote oneself, and a representative example is an ID photo.

An ID photo is a portrait that is attached to ID cards and documents for the purpose of judging a person and identifying other people's disguises. It is used for official documents such as passports and driver's licenses, private documents such as resumes, and applications such as entrance exams and qualification tests. Basically, the photo is taken with the face on the shoulder against a solid color background, without wearing a hat, mask, or sunglasses.

Conventionally, people visited professional photo studios to take ID photos, but visiting a studio to take ID photos has the disadvantage of being expensive and time-consuming.

In contrast to this conventional method (visiting a professional photo studio), recently, a method in which users take their own ID photos (for example, a self-ID photo shooting method) has been in the spotlight. The self-identification photo shooting method has the advantage of being able to take photos freely without interference from others, and reducing cost burden and time. In particular, as social distancing is implemented due to highly contagious viruses such as COVID-19, interest in this method of taking self-identification photos is increasing.

Meanwhile, in the case of the self-ID photo shooting method, the user not only takes the ID photo himself, but also has to perform corrections to the ID photo himself, so the quality of the result varies greatly depending on the user's correction ability. For users who lack this, the problem is that it is difficult to obtain high-quality results.

The problem to be solved by the present invention is to solve the problems of the conventional self-identification photo shooting method described above, by extracting features from an image including the user's face and using the extracted features to identify the user's face. A method, device, and computer program for providing an automated correction service for a user's profile image that can guide users who lack photo correction skills to obtain high-quality results by providing an automated correction service that performs correction is to provide.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

A method of providing an automated correction service for a user's profile image according to an embodiment of the present invention to solve the above-described problem is performed by a computing device, comprising: acquiring an image including the user's face; It may include extracting features by analyzing the obtained image and performing correction on the user's face included in the image using the extracted features.

In various embodiments, the step of extracting the features includes identifying a facial area corresponding to the user's face from the acquired image, dividing the identified facial area to generate a plurality of unit facial areas, and Analyzing the plurality of generated unit face areas to extract, as features, a plurality of tone values corresponding to each of the generated plurality of unit face areas, wherein performing correction on the user's face includes: , It may include performing tone correction on the identified facial area using at least one tone value among the plurality of extracted tone values.

In various embodiments, the step of performing tone correction on the identified facial region includes sorting the extracted plurality of tone values in ascending order, and selecting the nth tone value among the plurality of tone values sorted in ascending order as the first tone value. selecting, sorting the extracted plurality of tone values in descending order, selecting the mth tone value among the plurality of tone values sorted in descending order as the first tone value, and the selected first tone value and the selected first tone value. It may include performing tone correction on the identified facial area using each of the two tone values.

In various embodiments, performing tone correction on the identified facial area includes defining a tone correction direction corresponding to a skin texture direction on the identified facial area and using the at least one tone value. Tone correction for the identified face area is repeatedly performed according to the defined tone correction direction, and the number of times to repeatedly perform tone correction for the identified face area is equal to the at least one tone value and the at least one tone value. It may include a step of being determined based on at least one of a difference in tone values corresponding to a position to be tone corrected using and an attribute of a background included in the acquired image.

In various embodiments, the step of extracting the feature includes identifying a facial area corresponding to the user's face from the acquired image and analyzing the identified facial area to determine the user's facial shape as a feature. The step of performing correction on the user's face includes setting a plurality of first areas on the identified face area based on the determined face shape of the user, and performing correction on the user's face. Performing shadow correction on a first area, setting a plurality of second areas on the identified face area based on the determined face shape of the user, and performing highlighting correction on the set plurality of second areas. It may include steps to be performed.

In various embodiments, the step of extracting the features includes identifying a facial area corresponding to the user's face from the acquired image and analyzing the identified facial area to use the user's eyebrow area and iris color as features. and performing correction on the user's face. The step of performing correction on the user's face may include performing correction on the extracted eyebrow area using the extracted iris color.

In various embodiments, the step of extracting the features includes, when a plurality of different facial regions are identified from the acquired image, extracting a plurality of features from each of the identified plurality of facial regions, The step of performing correction on the user's face includes selecting at least one feature from among the plurality of extracted features and performing the same correction on the identified plurality of facial regions using the selected at least one feature. May include steps.

In various embodiments, the step of performing correction on the user's face includes receiving at least one keyword from a plurality of keywords, wherein the plurality of keywords are adjective keywords indicating the nature or state of the image. , based on the inputted at least one keyword, determining correction properties for the image, the correction properties including correction, degree of correction, and direction of correction, and determining correction properties of the user based on the determined correction properties. It may include performing correction on the face.

An automated correction service providing device for a user's profile image according to another embodiment of the present invention to solve the above-described problem includes a processor, a network interface, a memory, and is loaded into the memory and executed by the processor. It includes a computer program, wherein the computer program includes instructions for acquiring an image including the user's face, instructions for analyzing the obtained image to extract features, and using the extracted features, It may include instructions for performing correction on the user's face included in the image.

A computer program according to another embodiment of the present invention for solving the above-mentioned problem is combined with a computing device, obtaining an image including the user's face, and extracting features by analyzing the obtained image. readable by a computing device to execute a method of providing an automated correction service for a user's profile image, including performing correction on the user's face included in the image using the extracted features. It can be stored on a recording medium.

Other specific details of the invention are included in the detailed description and drawings.

According to various embodiments of the present invention, by providing an automated correction service that extracts features from an image including the user's face and performs correction on the user's face using the extracted features, correction skill for photos is provided. The advantage is that even users with limited skills can be guided to obtain high-quality results.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

Figure 1 is a diagram illustrating a system for providing an automated correction service for a user's profile image according to an embodiment of the present invention.
Figure 2 is a hardware configuration diagram of an automated correction service providing device for a user's profile image according to another embodiment of the present invention.
Figure 3 is a flowchart of a method for providing an automated correction service for a user's profile image according to another embodiment of the present invention.
FIG. 4 is a flowchart illustrating a method of performing tone correction on a user's face, according to various embodiments.
FIG. 5 is a diagram illustrating an example of a tone correction direction applicable to various embodiments.
FIG. 6 is a flowchart illustrating a method of performing shading and highlighting correction on a user's face, according to various embodiments.
FIG. 7 is a diagram illustrating first and second regions according to face shape applicable to various embodiments.
FIG. 8 is a flowchart illustrating a method for performing correction on a user's eyebrow area, according to various embodiments.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure of the present invention is complete and to provide a general understanding of the technical field to which the present invention pertains. It is provided to fully inform the skilled person of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements. Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and every combination of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be a second component within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly specifically defined.

As used in the specification, the term “unit” or “module” refers to a hardware component such as software, FPGA, or ASIC, and the “unit” or “module” performs certain roles. However, “part” or “module” is not limited to software or hardware. A “unit” or “module” may be configured to reside on an addressable storage medium and may be configured to run on one or more processors. Thus, as an example, a “part” or “module” refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within components and “parts” or “modules” can be combined into smaller components and “parts” or “modules” or into additional components and “parts” or “modules”. Could be further separated.

Spatially relative terms such as “below”, “beneath”, “lower”, “above”, “upper”, etc. are used as a single term as shown in the drawing. It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms that include different directions of components during use or operation in addition to the directions shown in the drawings. For example, if a component shown in a drawing is flipped over, a component described as “below” or “beneath” another component will be placed “above” the other component. You can. Accordingly, the illustrative term “down” may include both downward and upward directions. Components can also be oriented in other directions, so spatially relative terms can be interpreted according to orientation.

In this specification, a computer refers to all types of hardware devices including at least one processor, and depending on the embodiment, it may be understood as encompassing software configurations that operate on the hardware device. For example, a computer can be understood to include, but is not limited to, a smartphone, tablet PC, desktop, laptop, and user clients and applications running on each device.

Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

Each step described in this specification is described as being performed by a computer, but the subject of each step is not limited thereto, and depending on the embodiment, at least part of each step may be performed in a different device.

Figure 1 is a diagram illustrating a system for providing an automated correction service for a user's profile image according to an embodiment of the present invention.

Referring to FIG. 1, the automated correction service provision system for a user's profile image according to an embodiment of the present invention includes an automated correction service provision device 100, a user terminal 200, an external server 300, and a network. It may include (400).

Here, the automated correction service provision system for the user's profile image shown in FIG. 1 is according to one embodiment, and its components are not limited to the embodiment shown in FIG. 1, and may be added or changed as necessary. Or it can be deleted.

In one embodiment, the automated correction service providing device 100 (hereinafter, “computing device 100”) provides an automated correction service for the image, that is, by acquiring an image including the user's face, the image included in the image is provided. A service that automatically corrects the user's face can be provided.

Here, the image including the user's face may refer to the user's profile image (eg, identification photo), but is not limited thereto.

In addition, here, the type of correction performed on the user's face may include, but is not limited to, at least one of tone correction, shadow correction (shading correction), highlighting correction, and eyebrow area correction for the user's face. , The types of corrections include correction of the background area of the image, correction of the user's posture and pose, correction of temperature, exposure, contrast and saturation of the image, correction of the shape of the image, correction of squint and blush, correction of shadows included in the image, RGB correction and noise. Additional corrections, etc. may be included.

In various embodiments, the automated correction service provided by the computing device 100 may be implemented in the form of a web or application, and includes an operating system capable of running application software such as a web or application. Automated correction services may be applied in various devices and provided in various forms, but are not limited to this.

For example, the automated correction service in the form of application software provided by the computing device 100 is provided by a user terminal 200 (e.g., a user's smartphone terminal, tablet PC, laptop, and desktop) including an operating system capable of running the application software. ), it will be implemented in the form of automatically correcting the image uploaded by the user (or the image taken through the camera provided in the user terminal 200) as the user terminal 200 executes the automated correction service. You can.

As another example, the automated correction service in the form of application software provided by the computing device 100 is applied to a photo booth, self-studio, etc. equipped with a computing device including an operating system capable of running application software, and is applied to the photo booth or self-studio. As the computing device executes an automated correction service, it can be implemented in the form of automatically correcting images taken with a camera in a photo booth or self-studio.

As another example, the automated correction service in the form of application software provided by the computing device 100 is applied to a camera embedded with a computing device including an operating system capable of running application software, so that the computing device embedded in the camera is automated. It can be implemented in the form of automatically correcting images captured by a camera as the correction service is executed.

In one embodiment, the user terminal 200 may be connected to the computing device 100 through the network 400, and the user may use the automated correction service provided by the computing device 100 through the user terminal 200. You can.

Here, the user terminal 200 includes an operating system for driving an automated correction service implemented in the form of a web or application, and is used to output a user interface (UI) generated as the automated correction service is executed. May include a display.

For example, the user terminal 200 may be a smart phone, but is not limited thereto, and is a wireless communication device that guarantees portability and mobility, including navigation, Personal Communication System (PCS), and Global System for Mobile (GSM). communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code) Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, smartpad, tablet PC, etc. can include all types of handheld-based wireless communication devices. there is.

Here, the network 400 may mean a connection structure that allows information exchange between nodes, such as a plurality of terminals and servers. For example, the network 400 includes a local area network (LAN), a wide area network (WAN), the World Wide Web (WWW), a wired and wireless data communication network, a telephone network, and a wired and wireless television communication network. can do.

In addition, here, the wireless data communication network includes 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), and Wi-Fi (Wi-Fi). Fi), Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, It may include, but is not limited to, a Near-Field Communication (NFC) network, a satellite broadcasting network, an analog broadcasting network, and a Digital Multimedia Broadcasting (DMB) network.

In one embodiment, the external server 300 may be connected to the computing device 100 through the network 400, and may be necessary for the computing device 100 to perform a method of providing an automated correction service for the user's profile image. Various information and data can be stored and managed, or various information and data generated as the computing device 100 performs a method of providing an automated correction service for the user's profile image can be collected, stored, and managed.

For example, the external server 300 may be a storage server separately provided outside the computing device 100, but is not limited thereto. Hereinafter, the hardware configuration of the computing device 100 that performs a method of providing an automated correction service for a user's profile image will be described with reference to FIG. 2.

Figure 2 is a hardware configuration diagram of an automated correction service providing device for a user's profile image according to another embodiment of the present invention.

Referring to FIG. 2, the computing device 100 includes one or more processors 110, a memory 120 that loads a computer program 151 executed by the processor 110, a bus 130, and a communication interface. It may include a storage 150 that stores 140 and a computer program 151. Here, only components related to the embodiment of the present invention are shown in Figure 2. Accordingly, anyone skilled in the art to which the present invention pertains will know that other general-purpose components may be included in addition to the components shown in FIG. 2.

The processor 110 controls the overall operation of each component of the computing device 100. The processor 110 includes a Central Processing Unit (CPU), Micro Processor Unit (MPU), Micro Controller Unit (MCU), Graphic Processing Unit (GPU), or any other type of processor well known in the art of the present invention. It can be.

Additionally, the processor 110 may perform operations on at least one application or program for executing methods according to embodiments of the present invention, and the computing device 100 may include one or more processors.

In various embodiments, the processor 110 includes random access memory (RAM) (not shown) and read memory (ROM) that temporarily and/or permanently store signals (or data) processed within the processor 110. -Only Memory, not shown) may be further included. Additionally, the processor 110 may be implemented in the form of a system on chip (SoC) that includes at least one of a graphics processing unit, RAM, and ROM.

Memory 120 stores various data, commands and/or information. Memory 120 may load a computer program 151 from storage 150 to execute methods/operations according to various embodiments of the present invention. When the computer program 151 is loaded into the memory 120, the processor 110 can perform the method/operation by executing one or more instructions constituting the computer program 151. The memory 120 may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

Bus 130 provides communication functionality between components of computing device 100. The bus 130 may be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

The communication interface 140 supports wired and wireless Internet communication of the computing device 100. Additionally, the communication interface 140 may support various communication methods other than Internet communication. To this end, the communication interface 140 may be configured to include a communication module well known in the technical field of the present invention. In some embodiments, communication interface 140 may be omitted.

Storage 150 may store the computer program 151 non-temporarily. When performing an automated correction service provision process for the user's profile image through the computing device 100, the storage 150 stores various information necessary to provide an automated correction service provision process for the user's profile image. You can.

The storage 150 is a non-volatile memory such as Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, a hard disk, a removable disk, or a device well known in the technical field to which the present invention pertains. It may be configured to include any known type of computer-readable recording medium.

The computer program 151, when loaded into the memory 120, may include one or more instructions that cause the processor 110 to perform methods/operations according to various embodiments of the present invention. That is, the processor 110 can perform the method/operation according to various embodiments of the present invention by executing the one or more instructions.

In one embodiment, the computer program 151 includes the steps of acquiring an image including the user's face, analyzing the obtained image to extract features, and using the extracted features to identify the user included in the image. It may include one or more instructions for performing an automated correction service providing method for a user's profile image, including the step of performing correction on the face of the user.

The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. The software module may be RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside on any type of computer-readable recording medium well known in the art to which the present invention pertains.

The components of the present invention may be implemented as a program (or application) and stored in a medium in order to be executed in conjunction with a hardware computer. Components of the invention may be implemented as software programming or software elements, and similarly, embodiments may include various algorithms implemented as combinations of data structures, processes, routines or other programming constructs, such as C, C++, , may be implemented in a programming or scripting language such as Java, assembler, etc. Functional aspects may be implemented as algorithms running on one or more processors. Hereinafter, with reference to FIGS. 3 to 8, a method for providing an automated correction service for a user's profile image performed by the computing device 100 will be described.

Figure 3 is a flowchart of a method for providing an automated correction service for a user's profile image according to another embodiment of the present invention.

Referring to FIG. 3, in step S110, the computing device 100 may acquire an image including the user's face.

In various embodiments, the computing device 100 may be connected to the user terminal 200 through the network 400, may provide a UI for image acquisition to the user terminal 200, and may receive correction from the user through the UI. You can upload the image you want.

In various embodiments, the computing device 100 may be directly connected to the camera module through the network 400, and when images are generated as the camera module operates, the computing device 100 may automatically collect images generated from the camera module. .

Here, the image is an image including the user's face, and may mean, for example, a profile photo, but is not limited thereto.

In step S120, the computing device 100 may extract a feature from the image acquired through step S110.

In various embodiments, the computing device 100 may extract features from the image by analyzing the image using a previously learned artificial intelligence model.

Here, the previously learned artificial intelligence model is an image analysis model, which is a model learned using a plurality of images (profile images) labeled with one or more feature information as learning data, and a specific image as input data. It may be a model that extracts one or more features.

An artificial intelligence model (e.g. a neural network) consists of one or more network functions, and one or more network functions may consist of a set of interconnected computational units, which can generally be referred to as ‘nodes’. These ‘nodes’ may also be referred to as ‘neurons’. One or more network functions are composed of at least one or more nodes. Nodes (or neurons) that make up one or more network functions may be interconnected by one or more ‘links’.

Within an artificial intelligence model, one or more nodes connected through a link can 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 output node may be determined based on data input to the input node. Here, the nodes 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 artificial intelligence model 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 an artificial intelligence model, one or more nodes are interconnected through one or more links to form an input node and output node relationship within the artificial intelligence model. The characteristics of the artificial intelligence model can be determined according to the number of nodes and links within the artificial intelligence model, the correlation between nodes and links, and the weight value assigned to each link. For example, if there are two artificial intelligence models with the same number of nodes and links and different weight values between the links, the two artificial intelligence models may be recognized as different from each other.

Some of the nodes constituting the artificial intelligence model may form one layer based on the distances from the initial 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 the layer is arbitrary for explanation purposes, and the order of the layer within the artificial intelligence model 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 artificial intelligence model into which data is directly input without going through links in relationships with other nodes. Alternatively, in an artificial intelligence model 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 artificial intelligence model. Additionally, hidden nodes may refer to nodes that constitute an artificial intelligence model rather than the first input node and the last output node. The artificial intelligence model according to an embodiment of the present invention may have more nodes in the input layer than the nodes in the hidden layer close to the output layer, and is an artificial intelligence model in which the number of nodes decreases as it progresses from the input layer to the hidden layer. You can.

An artificial intelligence model may include one or more hidden layers. The hidden node of the hidden layer can take the output of the previous layer and the output of surrounding hidden nodes as input. The number of hidden nodes for each hidden layer may be the same or different. The number of nodes in the input layer may be determined based on the number of data fields of the input data and may be the same as or different from the number of hidden nodes. Input data input to the input layer can be operated by the hidden node of the hidden layer and output by the fully connected layer (FCL), which is the output layer.

In various embodiments, the artificial intelligence model may be a deep learning model.

A deep learning model (e.g., deep neural network (DNN)) may refer to an artificial intelligence model that includes multiple hidden layers in addition to the input layer and output layer. Using a deep neural network, data Latent structures can be identified, that is, the latent structures of photos, text, video, voice, and music (e.g., what objects are in the photo, what the content and emotion of the text are, and what the sound of the voice is like). content, emotions, etc.).

Deep neural networks include convolutional neural networks (CNN), recurrent neural networks (RNN), auto encoders, generative adversarial networks (GAN), and restricted Boltzmann machines (RBMs). Boltzmann machine), deep belief network (DBN), Q network, U network, Siamese network, etc., but are not limited to these.

In various embodiments, a network function may include an autoencoder. Here, the autoencoder may be a type of artificial neural network for outputting 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). The nodes of the dimensionality reduction layer and dimensionality restoration layer may or may not be symmetric. Additionally, autoencoders can perform non-linear dimensionality reduction. The number of input layers and output layers may correspond to the number of sensors remaining 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, and semi-supervised learning. Learning of a neural network is intended to minimize errors in output. More specifically, learning of a neural network repeatedly inputs learning data into the neural network, calculates the output of the neural network and the error of the target for the learning data, and converts the error of the neural network into the output of the neural network in a way to reduce the error. This is the process of updating the weight of each node in the neural network by backpropagating from the layer to the input layer.

First, in the case of teacher learning, learning data in which the correct answer is labeled for 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.

Next, 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, or dropout, which omits some of the network nodes during the learning process, can be applied.

In step S130, the computing device 100 may perform correction on the user's face included in the image using the features extracted through step S120. Hereinafter, with reference to FIGS. 4 to 8, a specific method of performing correction on the user's face will be described.

FIG. 4 is a flowchart illustrating a method of performing tone correction on a user's face, according to various embodiments.

Referring to FIG. 4 , in step S210, the computing device 100 may identify a facial area corresponding to the user's face by analyzing the image.

In various embodiments, the computing device 100 may identify the face area included in the image by analyzing the image using a previously learned face identification model using a plurality of images including the face area as learning data. Here, the previously learned face identification model may be implemented in the same or similar form as the above artificial intelligence model, but is not limited to this.

In step S220, the computing device 100 may extract a tone value for the face region as a feature for performing tone correction by analyzing the face region identified through step S210.

In various embodiments, the computing device 100 may generate a plurality of unit face areas by dividing the face area by gridding the face area, and may generate a plurality of unit face areas by analyzing each of the plurality of unit face areas. A plurality of tone values corresponding to each can be extracted.

Here, the tone value corresponding to each of the plurality of unit face areas may include a color value and a brightness value for each of the plurality of unit face areas, but is not limited to this.

In various embodiments, the computing device 100 has the same tone value when the tone value corresponding to two or more adjacent unit face areas among the plurality of unit face areas is the same or has a difference value within a preset range. Two or more unit face areas with differences within a preset range can be grouped into one group.

In various embodiments, the computing device 100 may group two or more unit face areas corresponding to the same direction among a plurality of unit face areas into one group based on the skin texture direction (eg, FIG. 5).

In this way, the same tone correction may be performed on two or more unit face areas grouped into one group, but the present invention is not limited to this.

In step S230, the computing device 100 may perform tone correction on the user's face using at least one tone value among the plurality of tone values extracted through step S220.

In various embodiments, the computing device 100 may sort a plurality of tone values in ascending order, select an n-th tone value from among the plurality of tone values sorted in ascending order, and use the selected n-th tone value to display the user's face. Tone correction can be performed.

For example, the computing device 100 sorts a plurality of tone values in ascending order and selects the nth tone value (e.g., the 2nd or 3rd tone value) among the plurality of tone values sorted in ascending order, thereby selecting 2 tone values in the face area. The second or third darkest tone value can be selected as the first tone value, and tone correction on the user's face can be performed using the selected first tone value.

At this time, the computing device 100 darkens the user's face by performing tone correction on the user's face using the first tone, but only applies the tone to the unit face area having a tone value larger than the first tone. Correction may be performed, but is not limited to this.

In various embodiments, the computing device 100 may sort a plurality of tone values in descending order, select an m-th tone value from among the plurality of tone values sorted in descending order, and use the selected m-th tone value to display the user's face. By performing tone correction for , the user's face can be darkened.

For example, the computing device 100 sorts a plurality of tone values in descending order and selects the mth tone value (e.g., the 2nd or 3rd tone value) among the plurality of tone values sorted in descending order, thereby selecting 2 tone values in the face area. The second or third brightest tone value can be selected as the second tone value, and the user's face can be brightened by performing tone correction on the user's face using the selected second tone value.

At this time, the computing device 100 brightens the user's face by performing tone correction on the user's face using the second tone, but only applies the tone to the unit face area having a tone value smaller than the second tone. Correction may be performed, but is not limited to this.

In various embodiments, the computing device 100 may define a tone correction direction corresponding to the skin texture direction on the face area, using at least one tone value, according to the tone correction direction defined on the face area. Tone correction can be performed on the face area. For example, as shown in FIG. 5, the computing device 100 may define a tone correction direction according to skin texture for the facial area identified from the image, and perform tone correction according to skin texture using at least one tone value. Tone correction can be performed depending on the direction.

At this time, the computing device 100 performs tone correction on the face area by repeatedly touching at least one tone value according to the tone correction direction using a preset tone correction tool (e.g., Photoshop brush, paint, etc.). However, the number of times to repeatedly perform tone correction for the face area, that is, the number of times to repeatedly touch at least one tone value using a preset tone correction tool, is to perform tone correction using at least one tone value and at least one tone value. It may be determined based on at least one of the difference in tone values corresponding to the location and the properties of the background included in the image.

For example, when the computing device 100 wants to perform tone correction for a specific location using the first tone value, the computing device 100 repeats the process for the specific location based on the difference between the first tone value and the tone value extracted from the specific location. The number of corrections (number of repeated touches) can be determined, and tone correction for a specific position can be performed by repeatedly applying the first tone value to the specific position as many times as the determined number of repeated corrections.

As another example, when the computing device 100 wishes to perform tone correction for a specific location using the first tone value, the computing device 100 may perform a specific location based on the difference between the first tone value and the tone value extracted from the background area included in the image. The number of repetition corrections (number of repeated touches) for a position can be determined, and tone correction for a specific position can be performed by repeatedly applying the first tone value to the specific position as many times as the determined repetition correction number.

In various embodiments, the computing device 100 may extract a plurality of tone values corresponding to each of a plurality of unit face regions as the facial area is analyzed, and select a maximum value and a minimum value among the plurality of extracted tone values. Tone correction for the face area can be performed only when the difference between the selected maximum and minimum values is greater than a preset standard, that is, when the difference between the darkest and brightest parts of the face area is large, and the maximum value is If the difference between and the minimum value is less than a preset standard, that is, if the difference between the darkest part and the brightest part of the face area is small, tone correction for the face area may not be performed.

In various embodiments, the computing device 100 performs tone correction on the face using at least one tone value among a plurality of tone values extracted by analyzing the face area, and performs tone correction on the face until a preset condition is satisfied. Calibration can be performed repeatedly.

Here, satisfying the preset condition may mean that the difference between the average tone value of the face area and at least one tone value is within an error range, but is not limited to this.

More specifically, first, the computing device 100 may select at least one tone value from among a plurality of tone values and perform tone correction on the face using the at least one selected tone value.

Thereafter, the computing device 100 may re-analyze the corrected facial area using at least one tone value to re-extract a plurality of tone values, and the average value of the plurality of re-extracted tone values and at least one tone By determining whether the difference in values is within the error range, it is possible to determine whether preset conditions are satisfied.

Thereafter, when it is determined that the preset condition is satisfied, that is, when it is determined that the difference between the average value of the plurality of re-extracted tone values and at least one tone value is within the error range, the computing device 100 determines that the facial area You can stop tone correction for to prevent further tone correction from being performed.

Meanwhile, when it is determined that the preset condition is not satisfied, that is, when the difference between the average value of the plurality of re-extracted tone values and at least one tone value is determined to be outside the error range, the computing device 100 determines that the preset condition is not satisfied, at least Tone correction for a previously corrected face area can be re-performed using a single tone value.

That is, the computing device 100 performs tone correction for the face area using at least one tone value among a plurality of tone values, but the difference between the average tone value for the face area and the at least one tone value is within the error range. Tone correction can be performed repeatedly until .

FIG. 6 is a flowchart illustrating a method of performing shading and highlighting correction on a user's face, according to various embodiments.

Referring to FIG. 6 , in step S310, the computing device 100 may identify a facial area corresponding to the user's face by analyzing the image. Here, the operation of identifying the face area from the image may be implemented in the same or similar form as step S210 of FIG. 4, but is not limited thereto.

In step S320, the computing device 100 may determine the user's face shape as a feature by analyzing the facial area identified through step S310.

In various embodiments, the computing device 100 may extract a vector indicating the outline of the face area with respect to the face area included in the image, determine the shape of the face area based on the extracted vector, and determine the shape of the face area. The user's face shape can be determined based on the shape of the area. However, it is not limited to this.

Here, the user's face shape may include, but is not limited to, oval shape, long shape, round shape, cheek shape, and angular shape.

In step S330, the computing device 100 may set a plurality of areas for shading correction and highlighting correction based on the user's face shape determined through step S320.

For example, as shown in FIG. 7, the position where shading correction is required and the position for highlighting correction may be different depending on the face shape (e.g., oval, long, round, cheek, angular, etc.), and the computing device 100 may set a plurality of first areas 10 for shading correction and a plurality of second areas 20 for highlighting correction on the face area according to the user's face shape.

In various embodiments, the computing device 100 includes a plurality of first areas 10 and a plurality of second areas 20 according to the user's face shape based on correction position data according to the face shape. It can be set on the face area.

Here, correction position data according to face shape may refer to data stored by matching information about the first area for shading correction and information about the second area for highlighting correction for each of a plurality of face shapes, and may refer to data stored by the administrator. It may mean data defined and stored in advance, but is not limited to this.

In step S340, the computing device 100 may perform shading correction for the plurality of first areas 10 set through step S330 and highlighting correction for the plurality of second areas 20. .

Here, shading correction refers to correction of darkening a specific area using a shadow correction tool (e.g., Photoshop's burn function), and highlighting correction refers to a highlighting correction tool (e.g., Photoshop's dodge function). This may mean correction of brightening a specific area using , but is not limited to this.

FIG. 8 is a flowchart illustrating a method for performing correction on a user's eyebrow area, according to various embodiments.

Referring to FIG. 8 , in step S410, the computing device 100 may identify a facial area corresponding to the user's face by analyzing the image.

In step S420, the computing device 100 may analyze the face area identified through step S410 and extract the user's eyebrow area and the user's iris color as features.

In step S430, the computing device 100 performs correction on the eyebrow area extracted through step S420, and may correct the user's eyebrow area using the user's iris color. However, it is not limited to this.

Referring again to FIG. 3 , in various embodiments, computing device 100 may perform correction on the user's face included in the image based on the nature and state of the image.

More specifically, first, computing device 100 may determine one or more keywords for the user. For example, the computing device 100 may provide a UI that outputs a keyword list including a plurality of keywords, and may allow the user to select one or more keywords among the plurality of keywords through the UI.

Here, the keyword is an adjective keyword that indicates the nature or state of the profile image (e.g., romantic, feminine, elegant, sexy, menish, classic, modern, sophisticated, avant-garde, futuristic, cyber-techno, kitsch, natural, It may mean (ethnic, sporty, casual, active, retro, luxury, etc.), but is not limited to this.

In various embodiments, the computing device 100 may determine attributes (e.g., personality, inclination, taste, etc.) for the user by analyzing a plurality of social data uploaded to the user's account, and may determine the attributes of the determined user. You can select one or more keywords for your users based on:

In general, SNS accounts are one's own space where one can express and reveal one's personality, inclinations, tastes, values, etc., and posts (e.g. posts or images, etc.) uploaded on SNS reflect the user's personality, It can be an important element that clearly reveals inclinations, tastes, and values.

Considering this, the computing device 100 can collect a plurality of social data uploaded to the user's account from the external server 300 (e.g., SNS operation server), analyze the data, and determine the user's attributes through this. (e.g. personality, inclination, taste and values) can be determined, and by extracting one or more keywords for the user according to the determined attributes, keywords corresponding to the user's personality, inclination, taste and values can be accurately extracted. There is an advantage to being able to do it.

Here, the method of determining a user's attributes by analyzing a plurality of social data is based on the operation of extracting one or more attribute keywords from text-type posts uploaded by the user through string analysis and keyword data for each attribute of the user that is already stored. A method including an operation of determining the user's attributes corresponding to the extracted attribute keywords may be applied, but is not limited to this.

In various embodiments, the computing device 100 provides answers to questions based on the MBTI test, such as personality type (e.g., energy direction (extroversion (E), introversion (I))), cognitive function (sensing (S)) for the user. ), intuition (N)), judgment function (thinking (T), emotion (F)), and lifestyle (judgment (J), perception (P))), and determine the personality type of the determined user. Based on this, one or more adjective keywords suitable for the user's personality type can be extracted. For example, in response to the user having an extroverted personality (E), the computing device 100 may include adjective keywords (e.g., bold, provocative, passionate, revealing, etc.) related to the user actively revealing and expressing himself. adjective keywords related to revealing and expressing oneself indirectly, without actively revealing oneself, in response to the user having an introverted personality (I) (e.g. neat, gentle, subtle, natural, calm, composed) etc.) can be selected.

Thereafter, the computing device 100 may determine correction properties including whether or not to correct the image, correction degree, and correction direction based on the keyword determined according to the above method, and correct the user's face according to the determined correction properties. can be performed.

For example, the computing device 100 may provide correction attribute information for each keyword defined in advance (information defined in advance for each of a plurality of keywords, such as whether to perform correction by type for each of the plurality of keywords, and a tone correction range (tone value range). ), including information such as the location and number of the first area and the second area), it is possible to determine whether or not to correct the user's face, the correction degree, and the direction of correction, and the determined correction, correction degree, and correction direction. Correction of the user's face can be performed depending on the direction.

In various embodiments, the computing device 100 may extract information about the user's facial expression as a feature by analyzing the user's face included in the image, and determine whether or not the image is corrected based on the extracted user's facial expression. Correction properties including degree and correction direction can be determined, and correction of the user's face can be performed according to the determined correction properties.

For example, the computing device 100 may provide predefined correction attribute information for each facial expression (information defined in advance for each of a plurality of facial expressions, such as whether or not to perform correction by type for each of the plurality of facial expressions, and a tone correction range (tone value range). ), including information such as the location and number of the first area and the second area), it is possible to determine whether or not to correct the user's face, the correction degree, and the direction of correction, and the determined correction, correction degree, and correction direction. Correction of the user's face can be performed depending on the direction.\

In various embodiments, the computing device 100 may analyze the image to extract information about the user's posture as a feature, including whether the image is corrected, the degree of correction, and the direction of correction based on the extracted user's posture. Correction properties can be determined, and correction of the user's face can be performed according to the determined correction properties.

For example, the computing device 100 may provide predefined correction attribute information for each posture (or pose) (information defined in advance for each of a plurality of postures (poses), and each type of correction for each of the plurality of postures (poses). Based on information such as whether to perform the correction, the tone correction range (tone value range), and the location and number of the first area and the second area, it is possible to determine whether to correct the user's face, the degree of correction, and the direction of correction. And, correction of the user's face can be performed according to the determined correction, degree of correction, and direction of correction.

In various embodiments, the computing device 100 may determine correction properties including whether to correct the image, correction degree, and correction direction, based on the age and gender of the user included in the image, and according to the determined correction properties. Correction can be performed on the user's face.

In various embodiments, the computing device 100 may provide correction properties including whether to correct the image, the degree of correction, and the direction of correction based on the use (or purpose of use) of the image (e.g., for collection, for issuing certificates, etc.). can be determined, and correction of the user's face can be performed according to the determined correction properties.

In various embodiments, when a plurality of face regions are identified in one image, the computing device 100 may individually extract features for each of the plurality of face regions by analyzing each of the plurality of face regions, and individually Correction for each of the plurality of face regions can be performed individually using the extracted features.

In various embodiments, when a plurality of facial regions are identified in one image, the computing device 100 may extract a plurality of features by analyzing each of the plurality of facial regions, and at least one of the plurality of extracted features The same correction can be performed on multiple facial areas using features.

For example, when two or more face regions are identified in one image, the computing device 100 may analyze the two or more face regions to extract a plurality of tone values for each of the two or more face regions, and may extract a plurality of tone values for each of the two or more face regions. Using each value, you can individually select two or more tone values to perform tone correction of two or more face areas, and you can use any one of the two or more individually selected tone values to perform tone correction for two or more face areas. By performing the same tone correction, two or more facial areas can have similar tones.

In various embodiments, when a plurality of face areas are identified in one image, the computing device 100 may set any one of the plurality of face areas as a reference, and by analyzing the face area set as a reference. The same correction can be performed on multiple face areas using the extracted features. For example, when a plurality of face regions are identified in one image, the computing device 100 may set the largest face region as a standard based on the sizes of the plurality of face regions, and analyze the face region set as the standard. Accordingly, the same correction can be performed on multiple face areas using the extracted features.

At this time, different facial areas may be set as standards depending on the type of correction. For example, when a first face area, a second face area, and a third face area are identified in one image, the computing device 100 uses the tone value extracted based on the first face area to create the first to third facial areas. Tone correction may be performed on the face area, and shadow and highlight correction may be performed on the first to third face areas based on the face shape extracted based on the second face area.

In various embodiments, when a plurality of face regions are identified in one image, the computing device 100 may extract a plurality of features by analyzing each of the plurality of face regions, and use the average of the extracted features. The same correction can be performed on multiple face areas. For example, when first to third facial regions are identified in one image, the computing device 100 may individually extract a plurality of tone values by analyzing each of the first to third facial regions, and individually Tone values for tone correction can be individually selected using a plurality of extracted tone values, and tone correction for the first to third facial regions can be performed in the same way using the average value of the selected tone values.

The method of providing an automated correction service for the user's profile image described above was explained with reference to the flow chart shown in the drawing. For simple explanation, the method of providing an automated correction service for a user's profile image is illustrated and described as a series of blocks, but the present invention is not limited to the order of the blocks, and some blocks are similar to those shown and performed herein. They may be performed in different orders or simultaneously. Additionally, new blocks not described in this specification and drawings may be added, or some blocks may be deleted or changed.

Above, embodiments of the present invention have been described with reference to the attached drawings, but those skilled in the art will understand that the present invention can be implemented in other specific forms without changing its technical idea or essential features. You will be able to understand it. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive.

100: Automated correction service provision device (computing device)
200: user terminal
300: external server
400: Network

Claims (10)

In a method performed by a computing device,
Obtaining an image including the user's face;
Analyzing the acquired image to extract features; and
Comprising: performing correction on the user's face included in the image using the extracted features,
The step of extracting the features is,
Identifying a facial area corresponding to the user's face from the acquired image;
dividing the identified face area to create a plurality of unit face areas; and
Analyzing the generated plurality of unit face regions and extracting, as features, a plurality of tone values corresponding to each of the generated plurality of unit face regions,
The step of performing correction on the user's face is,
Comprising: performing tone correction on the identified facial area using at least one tone value among the plurality of extracted tone values,
The step of performing tone correction on the identified facial area includes:
Sorting the extracted plurality of tone values in ascending order and selecting an nth tone value among the plurality of tone values sorted in ascending order as a first tone value;
Sorting the extracted plurality of tone values in descending order and selecting an mth tone value among the plurality of tone values sorted in descending order as a second tone value; and
Comprising performing tone correction on the identified facial area using each of the selected first tone value and the selected second tone value,
A method of providing an automated correction service for a user's profile image. delete delete According to paragraph 1,
The step of performing tone correction on the identified facial area includes:
defining a tone correction direction corresponding to a skin texture direction on the identified facial area; and
Tone correction for the identified face area is repeatedly performed according to the defined tone correction direction using the at least one tone value, and the number of times to repeatedly perform tone correction for the identified face area is the at least one tone correction. Determined based on at least one of a tone value, a difference between a tone value corresponding to a position to be tone corrected using the at least one tone value, and an attribute of a background included in the acquired image, comprising:
A method of providing an automated correction service for a user's profile image. According to paragraph 1,
The step of extracting the features is,
Identifying a facial area corresponding to the user's face from the acquired image; and
Analyzing the identified facial area to determine the user's facial shape as a feature,
The step of performing correction on the user's face is,
Based on the determined face shape of the user, setting a plurality of first areas on the identified face area and performing shadow correction on the set plurality of first areas; and
Comprising the step of setting a plurality of second areas on the identified face area based on the determined face shape of the user and performing highlighting correction on the set plurality of second areas,
A method of providing an automated correction service for a user's profile image. According to paragraph 1,
The step of extracting the features is,
Identifying a facial area corresponding to the user's face from the acquired image; and
Analyzing the identified facial area to extract the user's eyebrow area and iris color as features,
The step of performing correction on the user's face is,
Comprising the step of performing correction on the extracted eyebrow area using the extracted iris color,
A method of providing an automated correction service for a user's profile image. According to paragraph 1,
The step of extracting the features is,
When a plurality of different facial regions are identified from the acquired image, extracting a plurality of features from each of the identified plurality of facial regions,
The step of performing correction on the user's face is,
Comprising the step of selecting at least one feature from among the plurality of extracted features and performing the same correction on the identified plurality of facial regions using the selected at least one feature,
A method of providing an automated correction service for a user's profile image. According to paragraph 1,
The step of performing correction on the user's face is,
Receiving at least one keyword from a plurality of keywords - the plurality of keywords being adjective keywords indicating the nature or state of an image - from the user;
Based on the at least one input keyword, determining correction properties for the image, the correction properties including correction status, correction degree, and correction direction; and
Comprising: performing correction on the user's face based on the determined correction attribute,
A method of providing an automated correction service for a user's profile image. processor;
network interface;
Memory; and
Includes a computer program loaded into the memory and executed by the processor,
The computer program is,
Instructions for obtaining an image including the user's face;
Instructions for extracting features by analyzing the acquired image; and
Includes instructions for performing correction on the user's face included in the image using the extracted features,
The instructions for extracting the above features are:
Instructions for identifying a facial area corresponding to the user's face from the acquired image;
Instructions for generating a plurality of unit face areas by dividing the identified face area; and
Includes instructions for analyzing the generated plurality of unit face regions and extracting, as features, a plurality of tone values corresponding to each of the generated plurality of unit face regions,
The instruction for performing correction on the user's face is,
Includes instructions for performing tone correction on the identified facial area using at least one tone value among the plurality of extracted tone values,
The instruction for performing tone correction for the identified facial area is:
an instruction for sorting the extracted plurality of tone values in ascending order and selecting an nth tone value among the plurality of tone values sorted in ascending order as a first tone value;
an instruction for sorting the extracted plurality of tone values in descending order and selecting an mth tone value among the plurality of tone values sorted in descending order as a second tone value; and
Comprising instructions for performing tone correction on the identified facial region using each of the selected first tone value and the selected second tone value,
An automated correction service provider for a user's profile image. Combined with a computing device,
Obtaining an image including the user's face;
Analyzing the acquired image to extract features; and
Comprising: performing correction on the user's face included in the image using the extracted features,
The step of extracting the features is,
Identifying a facial area corresponding to the user's face from the acquired image;
dividing the identified face area to create a plurality of unit face areas; and
Analyzing the generated plurality of unit face regions and extracting, as features, a plurality of tone values corresponding to each of the generated plurality of unit face regions,
The step of performing correction on the user's face is,
Comprising: performing tone correction on the identified facial area using at least one tone value among the plurality of extracted tone values,
The step of performing tone correction on the identified facial area includes:
Sorting the extracted plurality of tone values in ascending order and selecting an nth tone value among the plurality of tone values sorted in ascending order as a first tone value;
Sorting the extracted plurality of tone values in descending order and selecting an mth tone value among the plurality of tone values sorted in descending order as a second tone value; and
Computing to execute a method of providing an automated correction service for a user's profile image, including performing tone correction on the identified facial area using each of the selected first tone value and the selected second tone value. A computer program stored on a recording medium that can be read by a device.