Device for creating accessibility-based person image, method, recording media and tablet PC

Abstract

The present disclosure may include: an input interface for inputting a person image component for producing a person image and a display unit for displaying the process of producing a person image; and a processor for controlling operations related to producing a person image. The processor extracts a 2D asset including at least one face, hair, hair accessory, hat, glasses, clothing, and background effect that is linked to the person image component and is pre-set based on the person image component input through the input interface, displays a first UI on the display unit to select a first UI corresponding to the face, hair, hair accessory, hat, glasses, clothing, and background effect, generates a 2D rendered 2D image based on the selected face, hair, hair accessory, hat, glasses, clothing, and background effect, and displays the generated 2D image on the display unit.

Description

Technology Field

[0001] The present disclosure relates to an accessibility-based person image generation device, method, recording medium, and tablet PCC. Background Technology

[0002] Recently, with the advancement of AI (Artificial Intelligence) technology, models that generate images or videos, such as GAN (Generative Adversarial Networks), VAE (Variational AutoEncoder), and Transformer, are being developed.

[0003] Through this, many companies provide services that generate person images, drawings, videos, etc.

[0004] However, conventional image generation devices had limitations in providing high-quality works while reducing the time and effort required to produce portrait images. Prior art literature

[0005] Republic of Korea Published Patent Application 10-2022-0120082 (Published Aug. 30, 2022) The problem to be solved

[0006] The purpose of the embodiments disclosed in this disclosure is to provide a method for anyone to easily and quickly create a person image anytime, anywhere, regardless of location.

[0007] In addition, the embodiments disclosed in this disclosure aim to provide high-quality works while reducing the time and effort required to produce character images.

[0008] In addition, the embodiments disclosed in this disclosure aim to provide a way for not only artists but also ordinary people without drawing skills to easily and quickly produce high-quality portrait images.

[0009] The problems that this disclosure aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0010] An accessibility-based person image generation device according to one aspect of the present disclosure for achieving the aforementioned technical problem comprises: an input interface for inputting a person image component for creating a person image and a display unit for displaying the process of creating the person image; and a processor for controlling operations related to the creation of the person image. The processor extracts a 2D asset including at least one face, hair, hair accessory, hat, glasses, clothing, and background effect that is linked to the person image component and is pre-set based on the person image component input through the input interface, displays the first UI on the display unit to select a first UI corresponding to the face, hair, hair accessory, hat, glasses, clothing, and background effect, generates a 2D rendered 2D image based on the selected face, hair, hair accessory, hat, glasses, clothing, and background effect, and displays the generated 2D image on the display unit.

[0011] In addition, the processor may be characterized by further extracting 2D assets including a preset art style, special effects, and tattoos linked to the person image component.

[0012] In addition, when extracting the 2D asset, the processor may be characterized by further extracting changeable face attribute data, hair attribute data, hair accessory attribute data, hat attribute data, glasses attribute data, clothing attribute data, background effect attribute data, art style attribute data, special effect attribute data, and tattoo attribute data of the person image component.

[0013] Additionally, when generating the 2D image, the processor may further input the face attribute data, the hair attribute data, the hair accessory attribute data, the hat attribute data, the glasses attribute data, the clothing attribute data, the background effect attribute data, the art style attribute data, the special effect attribute data, and the tattoo attribute data into a generative artificial intelligence model, and further display the second UI on the display unit so as to select the second UI corresponding to the generative face data, hair data, hair accessory data, hat data, glasses data, clothing data, background effect data, art style data, special effect data, and tattoo data that are learned and output through the generative artificial intelligence model.

[0014] Additionally, when generating the 2D image, the processor may further input user attribute data, face attribute data, hair attribute data, hair accessory attribute data, hat attribute data, glasses attribute data, clothing attribute data, background effect attribute data, art style attribute data, special effect attribute data, and tattoo attribute data input through the input interface into a customized artificial intelligence model, and further display the third UI on the display unit so that the user can select the third UI corresponding to the customized person data that is learned and recommended through the customized artificial intelligence model.

[0015] Additionally, the processor may be characterized by further calculating pixel values ​​of the 2D image when generating the 2D image, further extracting texture mapping information and lighting effect information that are pre-set in conjunction with the pixel values ​​of the 2D image, and applying the texture mapping information and the lighting effect information to the 2D image to further generate a final 2D image.

[0016] Additionally, when the processor generates the 2D image, if a person image component based on a natural language processing model is input through the input interface, it further acquires a user input sentence corresponding to the input person image component, further divides the face element, hair element, hair accessory element, hat element, glasses element, clothing element, background effect element, art style element, special effect element, and tattoo element from the input sentence, and further generates the 2D image based on the face element, hair element, hair accessory element, hat element, glasses element, clothing element, background effect element, art style element, special effect element, and tattoo element.

[0017] Additionally, a method for generating a person image performed by an accessibility-based person image generation device according to another aspect of the present disclosure may include: providing an input interface to input a person image component for generating the person image; extracting a 2D asset including at least one face, hair, hair accessory, hat, glasses, clothing, and background effect that is linked to the person image component and is pre-set, based on the person image component input through the input interface; displaying a first UI to select a first UI corresponding to the face, hair, hair accessory, hat, glasses, clothing, and background effect; generating a 2D rendered 2D image based on the selected face, hair, hair accessory, hat, glasses, clothing, and background effect; and displaying the generated 2D image.

[0018] Additionally, a tablet PC according to another aspect of the present disclosure may include: an input interface for inputting a person image component for creating a person image and a display unit for displaying the process of creating the person image; and a processor for controlling operations related to the creation of the person image. The processor extracts a 2D asset including at least one face, hair, hair accessory, hat, glasses, clothing, and background effect that is linked to the person image component and is pre-set based on the person image component input through the input interface, displays the UI on the display unit to select a UI corresponding to the face, hair, hair accessory, hat, glasses, clothing, and background effect, generates a 2D rendered 2D image based on the selected face, hair, hair accessory, hat, glasses, clothing, and background effect, and displays the generated 2D image on the display unit.

[0019] In addition to this, a computer program stored on a computer-readable recording medium for executing the present disclosure may be further provided.

[0020] In addition, a computer-readable recording medium for recording a computer program for executing a method for implementing the present disclosure may be further provided. Effects of the invention

[0021] According to the aforementioned means for solving the problem of the present disclosure, anyone can easily and quickly produce a person image anytime, anywhere, regardless of location.

[0022] In addition, according to the aforementioned means for solving the problem of the present disclosure, it is possible to provide a high-quality work while reducing the time and effort required to produce a person image.

[0023] In addition, according to the aforementioned means for solving the problem of the present disclosure, not only artists but also ordinary people without drawing skills can easily and quickly produce high-quality character images.

[0024] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing

[0025] FIG. 1 is a diagram illustrating an example in which an accessibility-based person image generation device of the present disclosure is provided as a tablet PC. Figure 2 is a drawing showing an accessibility-based person image generation device of Figure 1. FIGS. 3 to 13 are drawings illustrating an accessibility-based person image generation process of the present disclosure as an example. Specific details for implementing the invention

[0026] Throughout this disclosure, the same reference numerals refer to the same components. This disclosure does not describe all elements of the embodiments, and general content in the art to which this disclosure pertains or content that overlaps between embodiments is omitted. The terms ‘part, module, component, block’ as used in the specification may be implemented in software or hardware, and depending on the embodiments, a plurality of ‘parts, modules, components, blocks’ may be implemented as a single component, or a single ‘part, module, component, block’ may include a plurality of components.

[0027] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are directly connected but also cases where they are indirectly connected, and indirect connections include connections made via a wireless communication network.

[0028] Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0029] Throughout the specification, when it is stated that a component is located "on" another component, this includes not only cases where a component is in contact with another component, but also cases where another component exists between the two components.

[0030] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0031] Singular expressions include plural expressions unless there is an obvious exception in the context.

[0032] In each step, identification codes are used for convenience of explanation and do not describe the order of the steps; the steps may be performed differently from the specified order unless a specific order is clearly indicated in the context.

[0033] The operating principles and embodiments of the present disclosure will be described below with reference to the attached drawings.

[0034] The present disclosure provides an input interface for inputting a person image component for creating a person image, extracts a 2D asset including at least one face, hair, hair accessory, hat, glasses, clothing, and background effect that is linked to the person image component and is pre-set based on the person image component input through the input interface, displays a first UI to select a first UI corresponding to the face, hair, hair accessory, hat, glasses, clothing, and background effect, generates a 2D rendered 2D image based on the selected face, hair, hair accessory, hat, glasses, clothing, and background effect, and can display the generated 2D image.

[0035] The present disclosure enables anyone to easily and quickly create portrait images anytime, anywhere, regardless of location. Furthermore, the present disclosure can provide high-quality works while reducing the time and effort required to create portrait images. Additionally, the present disclosure allows not only artists but also ordinary people without drawing skills to easily and quickly create high-quality portrait images.

[0036] Below, we will examine in detail the accessibility-based person image generation device of the present disclosure.

[0037] FIG. 1 is a diagram illustrating an example in which an accessibility-based person image generation device of the present disclosure is provided as a tablet PC. FIG. 2 is a diagram illustrating the accessibility-based person image generation device of FIG. 1.

[0038] FIGS. 3 to 13 are drawings illustrating an accessibility-based person image generation process of the present disclosure as an example.

[0039] Referring to FIGS. 1 and 2, the image generating device (100) may be provided as a tablet PC and may include a display unit (110), memory (120), and a processor (130).

[0040] The display unit (110) provides an input interface for inputting character image components for character image production and can display the process of character image production.

[0041] The control unit may be implemented with a memory (120) that stores data for an algorithm or a program that reproduces the algorithm for controlling the operation of components within the device, and at least one processor (130) that performs the aforementioned operation using the data stored in the memory (120). Here, the memory (120) and the processor (130) may each be implemented as separate chips. Additionally, the memory (120) and the processor (130) may be implemented as a single chip.

[0042] The memory (120) can store data supporting various functions of the device and a program for the operation of the control unit, and can store input / output data, and can store a number of application programs (or applications) running on the device, data for the operation of the device, and instructions. At least some of these application programs can be downloaded from an external server via wireless communication.

[0043] Such memory (120) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., 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), magnetic memory, magnetic disk, and optical disk. Additionally, the memory (120) may be a database that is separated from the device but connected via wired or wireless connection.

[0044] The memory (120) can store data related to the creation of a person image. The processor (130) can control operations related to the creation of a person image.

[0045] The processor (130) may provide an input interface to input character image components for creating a character image. Here, the character image components may be a face, hair, hair accessories, a hat, glasses, clothing, background effects, art style, special effects, and tattoos for creating a character image.

[0046] The processor (130) can extract 2D assets including at least one face, hair, hair accessory, hat, glasses, clothing, and background effect that are pre-set and linked to the person image component, based on the person image component input through the input interface. Additionally, the processor (130) can further extract 2D assets including a pre-set art style, special effects, and tattoos that are linked to the person image component.

[0047] At this time, when the processor (130) extracts 2D assets, it can further extract changeable face attribute data, hair attribute data, hair accessory attribute data, hat attribute data, glasses attribute data, clothing attribute data, background effect attribute data, art style attribute data, special effect attribute data and tattoo attribute data of the person image component.

[0048] The processor (130) can display a first UI on the display unit (110) to select a first UI corresponding to a face, hair, hair accessory, hat, glasses, clothing, and background effect. Additionally, the processor (130) can further display a first UI on the display unit (110) to select a first UI corresponding to a style, special effect, and tattoo.

[0049] The processor (130) can generate a 2D rendered image based on a selected face, hair, hair accessory, hat, glasses, clothing, and background effect. Additionally, the processor (130) can generate a 2D rendered image based on a selected art style, special effects, and tattoo. At this time, the processor (130) can display the generated 2D image on the display unit (110).

[0050] For example, when the processor (130) generates a 2D image, it may also input face attribute data, hair attribute data, hair accessory attribute data, hat attribute data, glasses attribute data, clothing attribute data, background effect attribute data, art style attribute data, special effect attribute data and tattoo attribute data into the generative artificial intelligence model.

[0051] At this time, the processor (130) may further display a second UI on the display unit (110) to allow further selection of a second UI corresponding to the generative face data, hair data, hair accessory data, hat data, glasses data, clothing data, background effect data, art style data, special effect data, and tattoo data that are learned and output through a generative artificial intelligence model.

[0052] As another example, when the processor (130) generates a 2D image, it may also input user attribute data, face attribute data, hair attribute data, hair accessory attribute data, hat attribute data, glasses attribute data, clothing attribute data, background effect data, art style attribute data, special effect attribute data and tattoo attribute data into a customized artificial intelligence model through an input interface.

[0053] At this time, the processor (130) may further display a third UI on the display unit (110) to allow further selection of a third UI corresponding to the customized person data that is learned and output through a customized artificial intelligence model.

[0054] When generating a 2D image, the processor (130) may further calculate pixel values ​​of the 2D image. Here, the processor (130) may further extract pre-set texture mapping information and lighting effect information associated with the pixel values ​​of the 2D image. At this time, the processor (130) may further generate a final 2D image by applying the texture mapping information and lighting effect information to the 2D image.

[0055] When the processor (130) generates a 2D image, if a person image component based on a natural language processing model is input through an input interface, it may further acquire a user's input sentence corresponding to the input person image component. Here, the processor (130) may further distinguish face elements, hair elements, hair accessory elements, hat elements, glasses elements, clothing elements, background effect elements, art style elements, special effect elements, and tattoo elements from the input sentence. At this time, the processor (130) may further generate a 2D image based on the face elements, hair elements, hair accessory elements, hat elements, glasses elements, clothing elements, background effect elements, art style elements, special effect elements, and tattoo elements.

[0056] Referring to FIGS. 3 to 13, the accessibility-based method for generating a person image may include a providing step (S210), an extraction step (S220), a display step (S230, S250), and a generation step (S240).

[0057] The processor (130) may provide an input interface through the display unit (110) to input character image components for creating a character image (S210). Here, the character image components may be a face, hair, hair accessories, a hat, glasses, clothing, background effects, art style, special effects, and tattoos for creating a character image. For example, the face may be various shapes of eyes, nose, mouth, ears, eyebrows, face shape, etc. As another example, hair, hair accessories, hats, glasses, and clothing may be various shapes of hair, various shapes of hair accessories, various shapes of hats, various shapes of glasses, various shapes of clothing, etc. As yet another example, the background effect may be various shapes of effects on the background surrounding the character, and the art style may be various works of Eastern and Western art, etc. As yet another example, the special effect may be various shapes of effects that have special techniques applied to the character, and the tattoo may be various shapes of tattoos, etc.

[0058] The processor (130) can extract 2D assets including at least one face, hair, hair accessory, hat, glasses, clothing, and background effect that are pre-set and linked to the person image component, based on the person image component input through the input interface (S220). Additionally, the processor (130) can further extract 2D assets including a pre-set art style, special effects, and tattoo that are linked to the person image component (S220).

[0059] At this time, when the processor (130) extracts 2D assets, it can further extract changeable face attribute data, hair attribute data, hair accessory attribute data, hat attribute data, glasses attribute data, clothing attribute data, background effect attribute data, art style attribute data, special effect attribute data and tattoo attribute data of the person image component.

[0060] For example, the processor (130) may extract 2D assets based on feature points of face attribute data, feature points of hair attribute data, feature points of hair accessory attribute data, feature points of hat attribute data, feature points of glasses attribute data, feature points of clothing attribute data, feature points of background effect attribute data, feature points of art style attribute data, feature points of special effect attribute data and feature points of tattoo attribute data.

[0061] At this time, the processor (130) may extract 2D assets including a changeable color form of face attribute data, a changeable color form of hair attribute data, a changeable color form of hair accessory attribute data, a changeable color form of hat attribute data, a changeable color form of glasses attribute data, a changeable color form of clothing attribute data, a changeable color form of background effect attribute data, a changeable color form of art style attribute data, a changeable color form of special effect attribute data, and a changeable color form of tattoo attribute data.

[0062] Additionally, the processor (130) may extract a 2D asset including a changeable position coordinate area of ​​face attribute data, a changeable position coordinate area of ​​hair attribute data, a changeable position coordinate area of ​​hair accessory attribute data, a changeable position coordinate area of ​​hat attribute data, a changeable position coordinate area of ​​glasses attribute data, a changeable position coordinate area of ​​clothing attribute data, a changeable position coordinate area of ​​background effect attribute data, a changeable position coordinate area of ​​art style attribute data, a changeable position coordinate area of ​​special effect attribute data, and a changeable position coordinate area of ​​tattoo attribute data.

[0063] Additionally, the processor (130) may extract 2D assets including a changeable pattern form of face attribute data, a changeable pattern form of hair attribute data, a changeable pattern form of hair accessory attribute data, a changeable pattern form of hat attribute data, a changeable pattern form of glasses attribute data, a changeable pattern form of clothing attribute data, a changeable pattern form of background effect attribute data, a changeable pattern form of art style attribute data, a changeable pattern form of special effect attribute data, and a changeable pattern form of tattoo attribute data.

[0064] The processor (130) can display a first UI on the display unit (110) to select a first UI corresponding to a face, hair, hair accessory, hat, glasses, clothing, and background effect (S230). Additionally, the processor (130) can further display a first UI on the display unit (110) to select a first UI corresponding to a style, special effect, and tattoo (S230).

[0065] For example, as illustrated in FIGS. 4 to 7, the processor (130) may display the 11th UI (D1) on the display unit (110) so that the processor selects the 11th UI (D1) corresponding to the face. Additionally, the processor (130) may display the 12th UI (D2) on the display unit (110) so that the processor selects the 12th UI (D2) corresponding to the hair. Additionally, the processor (130) may display the 13th UI (D3) on the display unit (110) so that the processor selects the 13th UI (D3) corresponding to the hair accessory. Additionally, the processor (130) may display the 14th UI (D4) on the display unit (110) so that the processor selects the 14th UI (D4) corresponding to the hat. Additionally, the processor (130) may display the 15th UI (D5) on the display unit (110) so that the processor selects the 15th UI (D5) corresponding to the glasses. Additionally, the processor (130) may display the 16th UI (D6) on the display unit (110) so that the processor selects the 16th UI (D6) corresponding to the costume. Additionally, the processor (130) may display the 17th UI (D7) on the display unit (110) so that the processor selects the 17th UI (D7) corresponding to the background effect.

[0066] As another example, as illustrated in FIGS. 4 to 7, the processor (130) may display the 18th UI (D8) on the display unit (110) so that the processor selects the 18th UI (D8) corresponding to a painting style. Additionally, the processor (130) may display the 19th UI (D9) on the display unit (110) so that the processor selects the 19th UI (D9) corresponding to a special effect. Additionally, the processor (130) may display the 20th UI (D10) on the display unit (110) so that the processor selects the 20th UI (D10) corresponding to a tattoo.

[0067] The processor (130) can generate a 2D rendered image based on a selected face, hair, hair accessory, hat, glasses, clothing, and background effect (S240). Additionally, the processor (130) can generate a 2D rendered image based on a selected art style, special effects, and tattoo (S240). At this time, the processor (130) can display the generated 2D images (C1 to C4) on the display unit (110) (S250).

[0068] For example, as illustrated in FIG. 8, when the processor (130) generates a 2D image, it can input face attribute data (ID1), hair attribute data (ID2), hair accessory attribute data (ID3), hat attribute data (ID4), glasses attribute data (ID5), clothing attribute data (ID6), background effect attribute data (ID7), art style attribute data (ID8), special effect attribute data (ID9), and tattoo attribute data (ID10) into a generative artificial intelligence model (AIM1).

[0069] Here, the generative artificial intelligence model (AIM1) can be constructed and reinforced trained using a training dataset with various face attribute data, various hair attribute data, various hair accessory attribute data, various hat attribute data, various glasses attribute data, various clothing attribute data, various background effect attribute data, various art style attribute data, various special effect attribute data, and various tattoo attribute data using a CNN algorithm or an RNN algorithm.

[0070] At this time, the processor (130) may further display a second UI on the display unit (110) to allow further selection of the second UI corresponding to the generative face data (OD1), generative hair data (OD2), generative hair accessory data (OD3), generative hat data (OD4), generative glasses data (OD5), generative clothing data (OD6), generative background effect data (OD7), generative art style data (OD8), generative special effect data (OD9) and generative tattoo data (OD10) that are learned and output based on the generative artificial intelligence model (AIM1). Here, the processor (130) can determine the face, hair, hair accessory, hat, glasses, clothing, background effect, art style, special effect, and tattoo, etc. by the selection of the second UI.

[0071] For example, as illustrated in FIGS. 4 to 7, the processor (130) may display the 21st UI (D21) on the display unit (110) to select the 21st UI (D21) corresponding to the generated face. Additionally, the processor (130) may display the 22nd UI (D22) on the display unit (110) to select the 22nd UI (D22) corresponding to the generated hair. Additionally, the processor (130) may display the 23rd UI (D23) on the display unit (110) to select the 23rd UI (D23) corresponding to the generated hair accessory. Additionally, the processor (130) may display the 24th UI (D24) on the display unit (110) to select the 24th UI (D24) corresponding to the generated hat. Additionally, the processor (130) may display the 25th UI (D25) on the display unit (110) to select the 25th UI (D25) corresponding to the generative glasses. Additionally, the processor (130) may display the 26th UI (D26) on the display unit (110) to select the 26th UI (D26) corresponding to the generative clothing. Additionally, the processor (130) may display the 27th UI (D27) on the display unit (110) to select the 27th UI (D27) corresponding to the generative background effect.

[0072] At this time, as illustrated in FIGS. 4 to 7, the processor (130) may display the 21st UI (D21) on the display unit (110) so that the processor selects the 21st UI (D21) corresponding to the generated face. Additionally, the processor (130) may display the 22nd UI (D22) on the display unit (110) so that the processor selects the 22nd UI (D22) corresponding to the generated hair. Additionally, the processor (130) may display the 24th UI (D24) on the display unit (110) so that the processor selects the 24th UI (D24) corresponding to the generated hat. Additionally, the processor (130) may display the 26th UI (D26) on the display unit (110) so that the processor selects the 26th UI (D26) corresponding to the generated clothing. Additionally, the processor (130) can display the 27th UI (D27) on the display unit (110) so that the 27th UI (D27) corresponding to the generative background effect is selected.

[0073] As another example, as illustrated in FIGS. 4 to 7, the processor (130) may display the 28th UI (D28) on the display unit (110) to select the 28th UI (D28) corresponding to a generative art style. Additionally, the processor (130) may display the 29th UI (D29) on the display unit (110) to select the 29th UI (D29) corresponding to a generative special effect. Additionally, the processor (130) may display the 30th UI (D30) on the display unit (110) to select the 30th UI (D30) corresponding to a generative tattoo.

[0074] At this time, as illustrated in FIG. 7, the processor (130) can display the 29th UI (D29) on the display unit (110) so that the 29th UI (D29) corresponding to the generative special effect is selected.

[0075] As another example, as illustrated in FIG. 9, when the processor (130) generates a 2D image, it may input face attribute data (ID1), hair attribute data (ID2), hair accessory attribute data (ID3), hat attribute data (ID4), glasses attribute data (ID5), clothing attribute data (ID6), background effect attribute data (ID7), art style attribute data (ID8), special effect attribute data (ID9), tattoo attribute data (ID10), and user attribute data (ID11) input through an interface into a customized artificial intelligence model (AIM2). Here, the user attribute data may be a pre-set face, age, gender, personality, art taste, etc.

[0076] At this time, the processor (130) may further display a third UI on the display unit (110) to allow further selection of a third UI corresponding to the recommended customized person data (OD11) learned based on the customized artificial intelligence model (AIM2). Here, the processor (130) can determine a customized person associated with the user's attributes by the selection of the third UI.

[0077] For example, as illustrated in FIG. 10, the processor (130) can display the 31st UI (D31) on the display unit (110) so that the 31st UI (D31) corresponding to the customized person data (OD11) is selected. At this time, the processor (130) can display the 31st UI (D31) on the display unit (110) so that the 31st UI (D31) corresponding to the customized person data linked to the user's attributes is selected based on the art style data.

[0078] As another example, as illustrated in FIG. 11, the processor (130) may display the 32nd UI (D32) on the display unit (110) to select the 32nd UI (D32) corresponding to the customized person data (OD11). At this time, the processor (130) may display the 32nd UI (D32) on the display unit (110) to select the 32nd UI (D32) corresponding to the customized person data linked to the user's attributes based on the specific person data.

[0079] Here, the custom artificial intelligence model (AIM2) can be constructed and reinforced using a training dataset with various face attribute data, various hair attribute data, various hair accessory attribute data, various hat attribute data, various glasses attribute data, various clothing attribute data, various background effect attribute data, various art style attribute data, various special effect attribute data, various tattoo attribute data, and various user attribute data using a CNN algorithm or an RNN algorithm.

[0080] In this disclosure, a second UI corresponding to a generated face, generated hair, generated hair accessory, generated hat, generated glasses, generated clothing, generated background effect, generated art style, generated special effect, and generated tattoo, which are learned and output based on a generated artificial intelligence model (132), can be displayed on a display unit (110) to allow selection, thereby making it easier and faster to create a person image.

[0081] Additionally, the present disclosure may further display a third UI on the display unit (110) to allow further selection of a third UI corresponding to a customized person that is learned and output based on a customized artificial intelligence model (133). Since the present disclosure can simultaneously provide a face, hair, hair accessories, hat, glasses, clothing, background effects, art style, special effects, and tattoos that are customized and linked to the user's attributes, the person image can be produced more easily and quickly.

[0082] Meanwhile, the processor (130) may display a third UI on the display unit (110) to select a third UI corresponding to priority-based customized person data linked to the user's attributes, based on art style data. Additionally, the processor (130) may display a third UI on the display unit (110) to select a third UI corresponding to priority-based customized person data linked to the user's attributes, based on specific person data.

[0083] Additionally, the processor (130) may display a third UI on the display unit (110) to allow the user to select a third UI corresponding to priority-based customized person data linked to the user's attributes, such as country, region, gender, age group, personality, and art taste, based on art style data. Additionally, the processor (130) may display a third UI on the display unit (110) to allow the user to select a third UI corresponding to priority-based customized person data linked to the user's attributes, such as country, region, gender, age group, personality, and art taste, based on specific person data.

[0084] Meanwhile, the processor (130) may further perform fine tuning on the customized person data (OD11).

[0085] Referring to FIG. 12, when the processor (130) generates a 2D image, it can calculate pixel values ​​of the 2D image (S261).

[0086] The processor (130) can extract pre-set texture mapping information and lighting effect information linked to the pixel values ​​of the 2D image (S262). At this time, the texture mapping information may represent colors or textures on objects within the 2D image, and the lighting effect information may represent lighting effects applied to objects or backgrounds within the 2D image.

[0087] The processor (130) applies texture mapping information and lighting effect information to the 2D image to generate a final 2D image (S263), and may display the generated final 2D image on the display unit (110) (S264).

[0088] The present disclosure can provide various 2D image effects in which texture mapping and lighting effects are efficiently applied.

[0089] Referring to FIG. 13, when the processor (130) generates a 2D image, if a person image component based on a Natural Language Processing (131) model is input through an input interface (S242a), the processor (130) can obtain a user's input sentence corresponding to the input person image component (S242b).

[0090] For example, the user's input sentence can be a face such as an egg face, a round face, or an angular face, hair such as a cut or a perm, or hair accessories such as a hair band or a hair pin.

[0091] As another example, the user's input sentence can be a hat such as a baseball cap, beret, or beanie; glasses such as round glasses, oval glasses, round sunglasses, or oval sunglasses; clothing such as a skirt or pants; or background effects such as the sea, mountains, snow, rain, aurora, or sunset.

[0092] As another example, the user's input text may be a painting style such as Kim Hong-do or Mona Lisa, special effects such as ears or phoenix wings, or a tattoo such as Oriental painting or watercolor.

[0093] The processor (130) can divide the face element, hair element, hair accessory element, hat element, glasses element, costume element, background effect element, art style element, special effect element and tattoo element from the input sentence (S242c).

[0094] For example, face elements can be oval, round, or angular face shapes, hair elements can be cuts or perms, and hair accessory elements can be hair bands or hair pins.

[0095] As other examples, hat elements can be baseball caps, berets, beanies, etc., glasses elements can be round glasses, oval glasses, round sunglasses, oval sunglasses, etc., clothing elements can be skirts or pants, etc., and background effect elements can be the sea, mountains, snow, rain, aurora, sunset, etc.

[0096] As another example, the art style element could be Kim Hong-do, Mona Lisa, etc., the special effect element could be ears, phoenix wings, etc., and the tattoo element could be Oriental painting or watercolor, etc.

[0097] The processor (130) can generate a 2D rendered image based on a face element, a hair element, a hair accessory element, a hat element, a glasses element, a costume element, a background effect element, a painting style element, a special effect element, and a tattoo element (S242d). For example, the processor (130) can generate a 2D rendered image based on a smiling man, DiCaprio, a haircut, a hat, a suit, eyes, a sunset, Kim Hong-do, and a phoenix.

[0098] The present disclosure, based on a natural language processing model (131), obtains a user input sentence corresponding to an input person image component, and divides the face element, hair element, hair accessory element, hat element, glasses element, clothing element, background effect element, art style element, special effect element and tattoo element of the sentence to generate a 2D rendered 2D image, thereby allowing the person image to be produced easily and quickly.

[0099] The present disclosure allows a user to select and freely arrange a face, hair, hair accessories, hat, glasses, clothing, background effects, art style, special effects, and tattoos to complete a person image.

[0100] The present disclosure provides essential tools and functions for creating a person image, thereby allowing the user to freely manipulate hair, hair accessories, hats, glasses, clothing, background effects, art style, special effects, tattoos, and screen angles and angle adjustments in a canvas area where a face can be selected and placed, thus enabling the creation of a person image more easily and conveniently. In this case, the present disclosure allows for intuitive editing of the face, hair, hair accessories, hats, glasses, clothing, background effects, art style, special effects, and tattoos. Furthermore, the present disclosure may provide a function to export to various document formats (PDF, PPT) and GIF files in addition to the person image file.

[0101] Since the present disclosure allows for easy editing in various styles and designs, not only artists but also ordinary people without drawing skills can produce high-quality portrait images more quickly and easily.

[0102] The present disclosure enables multiple artists to collaborate on producing portrait images through a sharing function, allows artists and general users to create high-quality works while reducing the time and effort required to produce portrait images, and enables more convenient management and sharing of works through a cloud-based service.

[0103] At least one component may be added or deleted in response to the performance of the components illustrated in FIGS. 1, 2, 4 through 11. Additionally, it will be readily understood by those skilled in the art that the relative positions of the components may be changed in response to the performance or structure of the system.

[0104] Although FIGS. 3, 12, and 13 describe the execution of multiple steps sequentially, this is merely an illustrative explanation of the technical concept of the present embodiment. A person skilled in the art to which the present embodiment belongs could modify and adapt the order described in FIGS. 3, 12, and 13, or execute one or more of the multiple steps in parallel, without departing from the essential characteristics of the present embodiment. Therefore, FIGS. 3, 12, and 13 are not limited to a chronological order.

[0105] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. The instructions may be stored in the form of program code and, when executed by a processor, may generate a program module to perform the operation of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0106] Computer-readable recording media include all types of recording media that store instructions that can be decoded by a computer. Examples include ROM (Read Only Memory), RAM (Random Access Memory), magnetic tape, magnetic disk, flash memory, optical data storage devices, etc.

[0107] As described above, the disclosed embodiments have been explained with reference to the attached drawings. Those skilled in the art will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be interpreted restrictively. Explanation of the symbols

[0108] 100: Image generating device 110: Display unit 120: Memory 130: Processor

Claims

Claim 1 An input interface for inputting character image components for character image production, and a display unit for displaying the process of character image production; and includes a processor that controls operations related to the production of the person image, wherein the processor extracts a 2D asset including at least one face, hair, hair accessory, hat, glasses, clothing, background effect, art style, special effect, and tattoo that is pre-set and linked to the person image component based on the person image component input through the input interface, displays the UI on the display unit so that the UI corresponding to the face, hair, hair accessory, hat, glasses, clothing, background effect, art style, special effect, and tattoo can be selected, generates a 2D rendered 2D image based on the selected face, hair, hair accessory, hat, glasses, clothing, background effect, art style, special effect, and tattoo, and displays the generated 2D image on the display unit, wherein when extracting the 2D asset, changeable art style attribute data included in the person image component is extracted, and when generating the 2D image, the art style attribute data input through the input interface is input into a customized artificial intelligence model, and based on the data learned through the customized artificial intelligence model, the user An accessibility-based person image generation device characterized by extracting customized person data according to priority based on country, region, gender, age group, personality, and art taste linked to attributes, and displaying a UI corresponding to the customized person data according to priority on the display unit so that it can be selected. Claim 2 delete Claim 3 An accessibility-based person image generation device according to claim 1, characterized in that, when extracting the 2D asset, the processor further extracts changeable face attribute data, hair attribute data, hair accessory attribute data, hat attribute data, glasses attribute data, clothing attribute data, background effect attribute data, special effect attribute data, and tattoo attribute data of the person image component. Claim 4 An accessibility-based person image generation device according to claim 3, wherein the processor, when generating the 2D image, further inputs the face attribute data, the hair attribute data, the hair accessory attribute data, the hat attribute data, the glasses attribute data, the clothing attribute data, the background effect attribute data, the special effect attribute data, and the tattoo attribute data into a generative artificial intelligence model, and further displays on the display unit a UI corresponding to the generative face data, hair data, hair accessory data, hat data, glasses data, clothing data, background effect data, special effect data, and tattoo data learned and output through the generative artificial intelligence model so as to enable selection. Claim 5 An accessibility-based person image generation device according to claim 3, wherein the processor, when generating the 2D image, further inputs user attribute data, face attribute data, hair attribute data, hair accessory attribute data, hat attribute data, glasses attribute data, clothing attribute data, background effect attribute data, special effect attribute data, and tattoo attribute data input through the input interface into a customized artificial intelligence model, further extracts customized person data based on data learned through the customized artificial intelligence model, and further displays a UI corresponding to the customized person data on the display unit so that it can be selected. Claim 6 An accessibility-based person image generation device according to claim 3, wherein the processor, when generating the 2D image, further calculates pixel values ​​of the 2D image, further extracts texture mapping information and lighting effect information pre-set in conjunction with the pixel values ​​of the 2D image, and applies the texture mapping information and the lighting effect information to the 2D image to further generate a final 2D image. Claim 7 An accessibility-based person image generation device according to claim 1, wherein, when generating the 2D image, the processor further acquires a user input sentence corresponding to the input person image component when a person image component based on a natural language processing model is input through the input interface, further divides the face element, hair element, hair accessory element, hat element, glasses element, clothing element, background effect element, art style element, special effect element, and tattoo element from the input sentence, and further generates the 2D image based on the face element, hair element, hair accessory element, hat element, glasses element, clothing element, background effect element, art style element, special effect element, and tattoo element. Claim 8 A method for generating a person image performed by an accessibility-based person image generation device, comprising: providing an input interface to input a person image component for producing the person image through a display unit of the person image generation device; extracting a 2D asset by a processor based on the person image component input through the input interface, the asset including at least one face, hair, hair accessory, hat, glasses, clothing, background effect, art style, special effect, and tattoo that is linked to and pre-set with the person image component; displaying a UI on a display unit of the person image generation device by the processor so that a UI corresponding to the face, hair, hair accessory, hat, glasses, clothing, background effect, art style, special effect, and tattoo can be selected; and generating a 2D rendered 2D image by the processor based on the selected face, hair, hair accessory, hat, glasses, clothing, background effect, art style, special effect, and tattoo. The method comprises the step of displaying the generated 2D image on the display unit, wherein the step of extracting the 2D asset extracts changeable art style attribute data included in the person image component by the processor when extracting the 2D asset, and the step of generating the 2D image inputs art style attribute data input through the input interface into a customized artificial intelligence model by the processor when generating the 2D image, extracts customized person data according to priority based on country, region, gender, age group, personality, and art work taste linked to user attributes based on data learned through the customized artificial intelligence model by the processor, and displays a UI corresponding to the customized person data according to priority on the display unit so that it can be selected by the processor. Claim 9 A display unit that provides an input interface for inputting character image components for character image production and displays the process of character image production; and a processor that controls operations related to character image production; The processor includes, based on a person image component input through the input interface, extracts a 2D asset including at least one face, hair, hair accessory, hat, glasses, clothing, background effect, art style, special effect, and tattoo that is pre-set and linked to the person image component; displays the UI on the display unit to enable selection of a UI corresponding to the face, hair, hair accessory, hat, glasses, clothing, background effect, art style, special effect, and tattoo; generates a 2D rendered 2D image based on the selected face, hair, hair accessory, hat, glasses, clothing, background effect, art style, special effect, and tattoo; and displays the generated 2D image on the display unit, wherein when extracting the 2D asset, modifiable art style attribute data included in the person image component is extracted; when generating the 2D image, the art style attribute data input through the input interface is input into a customized artificial intelligence model; and based on the data learned through the customized artificial intelligence model, country, region, gender, linked to user attributes, A tablet PC characterized by extracting customized person data according to priority based on age group, personality, and taste for art works, and displaying a UI corresponding to the customized person data according to priority on the display unit so that it can be selected. Claim 10 A computer-readable recording medium combined with a computer and storing a program for executing the method of claim 8.

Images