KR20240024535A - Method, computer device, and computer program to create new face using hidden face feature - Google Patents

Abstract

A method, computer device, and computer program for generating a new face using hidden facial features are disclosed. A method of generating a new face includes extracting a face area from a first source image and a second source image; combining a face area extracted from the first source image and a face area extracted from the second source image; generating a result image by combining the synthesized face area with a target image set as a style source; and generating a new result image by re-synthesizing a facial feature filter on the synthesized face area.

Description

Method, computer device, and computer program for generating a new face using hidden face features {METHOD, COMPUTER DEVICE, AND COMPUTER PROGRAM TO CREATE NEW FACE USING HIDDEN FACE FEATURE}

The explanation below is about face synthesis technology using deep learning.

Face conversion technology using artificial intelligence is developing to a level where converted faces can be created with high resolution.

Face transformation technology can be provided to users in a variety of ways. For example, a specific face can be composited with a user-desired background, thereby allowing the user or another person's face to appear in the user-desired background. You can also change the face of a famous person in a video to your own or someone else's face.

For example, Korea Patent Publication No. 10-1871662 (registration date June 21, 2018) discloses an image synthesis technology based on face detection.

We provide methods and devices that can diversify face synthesis results to create new faces.

We provide a method and device for generating a new face by applying a hidden face feature to the result of face synthesis using a source image.

An image compositing method executed on a computer device, wherein the computer device includes at least one processor configured to execute computer-readable instructions included in a memory, and the image compositing method includes: Extracting a face area from a first source image and a second source image; combining, by the at least one processor, a face area extracted from the first source image and a face area extracted from the second source image; generating a result image by combining the synthesized face area with a target image set as a style source, by the at least one processor; and generating a new result image by re-synthesizing a facial feature filter on the synthesized face area, by the at least one processor.

According to one aspect, the image synthesis method further includes building a filter database composed of a plurality of face feature filters by the at least one processor, and generating the new result image includes: It may include re-synthesizing the facial feature filter selected from to the synthesized face region.

According to another aspect, the filter database may be composed of a plurality of face feature filters made of different face features.

According to another aspect, the face feature filter included in the filter database may correspond to an image effect filter in which face features corresponding to at least some elements included in the face area are enhanced.

According to another aspect, the face feature filter included in the filter database may include at least one of an image effect filter comprised of human face features and an image effect filter comprised of animal face features.

According to another aspect, generating the new result image may include randomly selecting a facial feature filter from the filter database according to a user's request.

According to another aspect, the constructing step includes identifying a user's preference for a face feature filter included in the filter database, and the generating the new result image includes filtering the filter according to a user's request. It may include selecting a facial feature filter based on the user preference from a database.

According to another aspect, the target image may correspond to an image selected by the user among the first source image and the second source image.

According to another aspect, the target image may correspond to a separate image selected by the user that is different from the first source image or the second source image.

According to another aspect, the step of combining the first facial features extracted from the face area of the first source image and the second facial features extracted from the face area of the second source image at a ratio set by the user. It may include generating a synthetic face area by mixing.

A computer program stored in a computer-readable recording medium is provided to execute the image synthesis method on the computer device.

A computer device comprising: at least one processor configured to execute computer readable instructions included in a memory, the at least one processor comprising: extracting a facial area from a first source image and a second source image; A process of combining a face area extracted from the first source image and a face area extracted from the second source image; A process of generating a result image by combining the synthesized face area with a target image set as a style source; and a computer device that processes a process of generating a new result image by re-synthesizing a facial feature filter to the synthesized face area.

According to embodiments of the present invention, in the process of face synthesis using a deep learning model, new results are provided by applying hidden face features to the result of face synthesis using a source image, thereby improving service quality and user experience through diversification of face synthesis. It can be improved.

1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention.
Figure 2 is a block diagram showing an example of a computer device according to an embodiment of the present invention.
Figure 3 is a flowchart showing an example of an image compositing method that can be performed by a computer device according to an embodiment of the present invention.
Figures 4 and 5 show examples of the image synthesis process in one embodiment of the present invention.
Figures 6 and 7 show an example of an image synthesis process using a face filter according to an embodiment of the present invention.
Figure 8 shows an example of a face synthesis service screen in one embodiment of the present invention.
Figure 9 shows an example of a face synthesis result according to an embodiment of the present invention.
Figure 10 shows an example of the result of face synthesis using a face filter in one embodiment of the present invention.

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

Embodiments of the present invention relate to face synthesis technology using deep learning.

Embodiments including those specifically disclosed herein can diversify face synthesis results by utilizing hidden facial features to create new faces.

The image synthesis system according to embodiments of the present invention may be implemented by at least one computer device, and the image synthesis method according to embodiments of the present invention is performed through at least one computer device included in the image synthesis system. It can be. At this time, the computer program according to an embodiment of the present invention may be installed and driven in the computer device, and the computer device may perform the image compositing method according to the embodiment of the present invention under the control of the driven computer program. . The above-described computer program can be combined with a computer device and stored in a computer-readable recording medium to execute the image compositing method on the computer.

1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention. The network environment in FIG. 1 shows an example including a plurality of electronic devices 110, 120, 130, and 140, a plurality of servers 150 and 160, and a network 170. Figure 1 is an example for explaining the invention, and the number of electronic devices or servers is not limited as in Figure 1. In addition, the network environment in FIG. 1 only explains one example of environments applicable to the present embodiments, and the environment applicable to the present embodiments is not limited to the network environment in FIG. 1.

The plurality of electronic devices 110, 120, 130, and 140 may be fixed terminals or mobile terminals implemented as computer devices. Examples of the plurality of electronic devices 110, 120, 130, and 140 include smart phones, mobile phones, navigation devices, computers, laptops, digital broadcasting terminals, PDAs (Personal Digital Assistants), and PMPs (Portable Multimedia Players). ), tablet PC, etc. For example, in FIG. 1, the shape of a smartphone is shown as an example of the electronic device 110. However, in embodiments of the present invention, the electronic device 110 actually communicates with other devices through the network 170 using a wireless or wired communication method. It may refer to one of various physical computer devices capable of communicating with electronic devices 120, 130, 140 and/or servers 150, 160.

The communication method is not limited, and may include not only a communication method utilizing a communication network that the network 170 may include (for example, a mobile communication network, wired Internet, wireless Internet, and a broadcast network), but also short-range wireless communication between devices. For example, the network 170 may include a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), and a broadband network (BBN). , may include one or more arbitrary networks such as the Internet. Additionally, the network 170 may include any one or more of network topologies including a bus network, star network, ring network, mesh network, star-bus network, tree or hierarchical network, etc. Not limited.

Each of the servers 150 and 160 is a computer device or a plurality of computers that communicate with a plurality of electronic devices 110, 120, 130, 140 and a network 170 to provide commands, codes, files, content, services, etc. It can be implemented with devices. For example, the server 150 may be a system that provides a service (for example, a face synthesis service) to a plurality of electronic devices 110, 120, 130, and 140 connected through the network 170.

Figure 2 is a block diagram showing an example of a computer device according to an embodiment of the present invention. Each of the plurality of electronic devices 110, 120, 130, and 140 described above or each of the servers 150 and 160 may be implemented by the computer device 200 shown in FIG. 2. For example, the image synthesis system according to embodiments of the present invention may be implemented by the computer device 200 shown in FIG. 2.

As shown in FIG. 2, this computer device 200 may include a memory 210, a processor 220, a communication interface 230, and an input/output interface 240. The memory 210 is a computer-readable recording medium and may include a non-permanent mass storage device such as random access memory (RAM), read only memory (ROM), and a disk drive. Here, non-perishable large-capacity recording devices such as ROM and disk drives may be included in the computer device 200 as a separate permanent storage device that is distinct from the memory 210. Additionally, an operating system and at least one program code may be stored in the memory 210. These software components may be loaded into the memory 210 from a computer-readable recording medium separate from the memory 210. Such separate computer-readable recording media may include computer-readable recording media such as floppy drives, disks, tapes, DVD/CD-ROM drives, and memory cards. In another embodiment, software components may be loaded into the memory 210 through the communication interface 230 rather than a computer-readable recording medium. For example, software components may be loaded into memory 210 of computer device 200 based on computer programs installed by files received over network 170.

The processor 220 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. Commands may be provided to the processor 220 by the memory 210 or the communication interface 230. For example, processor 220 may be configured to execute received instructions according to program code stored in a recording device such as memory 210.

The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (eg, the storage devices described above) through the network 170. For example, a request, command, data, file, etc. generated by the processor 220 of the computer device 200 according to a program code stored in a recording device such as memory 210 is transmitted to the network ( 170) and can be transmitted to other devices. Conversely, signals, commands, data, files, etc. from other devices may be received by the computer device 200 through the communication interface 230 of the computer device 200 via the network 170. Signals, commands, data, etc. received through the communication interface 230 may be transmitted to the processor 220 or memory 210, and files, etc. may be stored in a storage medium (as described above) that the computer device 200 may further include. It can be stored as a permanent storage device).

The input/output interface 240 may be a means for interfacing with the input/output device 250. For example, input devices may include devices such as a microphone, keyboard, or mouse, and output devices may include devices such as displays and speakers. As another example, the input/output interface 240 may be a means for interfacing with a device that integrates input and output functions, such as a touch screen. The input/output device 250 may be configured as a single device with the computer device 200.

Additionally, in other embodiments, computer device 200 may include fewer or more components than those of FIG. 2 . However, there is no need to clearly show most prior art components. For example, the computer device 200 may be implemented to include at least some of the input/output devices 250 described above, or may further include other components such as a transceiver, a database, etc.

Hereinafter, specific embodiments of a method and device for generating a new face using hidden face features will be described.

Since the face synthesis process using a deep learning model synthesizes only the facial features included in the source image, the synthesis result is standardized to resemble the face in the source image, making it difficult to create a new third person.

These embodiments can go beyond standardized results and create new faces in various categories through synthesis using hidden facial features in the face synthesis process using a deep learning model.

The computer device 200 according to this embodiment can provide a face synthesis service to clients through a dedicated application installed on the client or through access to a web/mobile site related to the computer device 200. The computer device 200 may be configured with a computer-implemented image synthesis system. For example, the image synthesis system may be implemented in the form of a program that operates independently, or may be implemented in the form of an in-app of a specific application so that it can operate on the specific application.

The processor 220 of the computer device 200 may be implemented as a component for performing the following image synthesis method. Depending on the embodiment, components of the processor 220 may be selectively included in or excluded from the processor 220. Additionally, depending on the embodiment, components of the processor 220 may be separated or merged to express the functions of the processor 220.

The processor 220 and its components can control the computer device 200 to perform the steps included in the image synthesis method below. For example, the processor 220 and its components may be implemented to execute instructions according to the code of an operating system included in the memory 210 and the code of at least one program.

Here, the components of the processor 220 may be expressions of different functions performed by the processor 220 according to instructions provided by program codes stored in the computer device 200.

The processor 220 may read necessary instructions from the memory 210 where instructions related to controlling the computer device 200 are loaded. In this case, the read command may include an command for controlling the processor 220 to execute steps that will be described later.

Steps included in the image synthesis method to be described later may be performed in an order different from the order shown, and some of the steps may be omitted or additional processes may be included.

Figure 3 is a flowchart showing an example of an image compositing method that can be performed by a computer device according to an embodiment of the present invention.

The image synthesis method according to this embodiment can be performed by the computer device 200 described above. In this case, the processor 220 of the computer device 200 may be implemented to execute control instructions according to the code of an operating system or at least one program included in the memory 210. Here, the processor 220 is a computer device (S310 to S340) such that the computer device 200 performs the steps (S310 to S340) included in the image synthesis method of FIG. 3 according to control instructions provided by the code stored in the computer device 200. 200) can be controlled.

Referring to FIG. 3, in step S310, the processor 220 may separate a face area and a style area representing the remaining background (appearance) area excluding the face area from the first source image and the second source image, respectively. In other words, the processor 220 separates the first face area and the first style area from the first source image through face detection technology, and separates the second face area and the second style area from the second source image. It can be separated.

In step S320, the processor 220 may synthesize the first face area separated from the first source image and the second face area separated from the second source image. The processor 220 creates a new face area (hereinafter referred to as 'third face') by combining the first face area and the second face area through face swap (e.g., Simple Swap), an artificial intelligence-based image synthesis technology. (referred to as ‘area’) can be created.

In step S330, the processor 220 may generate a result image by combining the third face area with an image set as a style source (hereinafter referred to as a 'target image'). The target image refers to the style source used as the background area (the remaining background area excluding the face area) of the resulting image. The style source refers to the targeting style to be reflected in the resulting image. Excluding the face area of the image set as the style source, the remaining background (appearance) area is applied as the style appearance of the resulting image. The processor 220 may provide an interface for selecting a target image. Through this interface, the target image selected by the user can be used as a style source for compositing with the third face area. Any one of the first source image and the second source image may be selected as the target image that is the style source, and depending on the embodiment, an image other than the first source image and the second source image may be selected as the target image. can be selected.

In step S340, the processor 220 may generate a new result image by re-synthesizing the hidden face features in the third face area according to the user's request. In these embodiments, a filter DB (database) can be built in advance to create a third new person using hidden facial features other than the facial features included in the source image, and at this time, the filter DB is composed of different facial features. It may be composed of a plurality of face feature filters. For example, a face filter refers to an image effect filter in which some facial features are enhanced. A filter effect that exaggerates at least some elements included in the facial area, such as eyes, nose, mouth, ears, forehead, cheeks, cheeks, and facial shape. can be provided. The face filter may include image effect filters with enhanced animal face features as well as human face features. The processor 220 may create a new face by applying a face filter to the third face area created from the source image. At this time, the processor 220 may apply a face filter randomly selected from the filter DB according to the user's request. Depending on the embodiment, user preferences for face filters included in the filter DB may be identified, and face filters may be selected and applied based on rankings according to user preferences. For example, among the resulting images from the face synthesis service, the user's preference for face filters can be determined by collecting the face filters applied to the images saved by the user. The processor 220 may apply the face filters included in the filter DB according to the user's request, starting with the user's most preferred face filter.

Figures 4 and 5 show examples of the image synthesis process in one embodiment of the present invention.

Referring to Figures 4 and 5, the processor 220 may receive a first source image 510 and a second source image 520, which are target images for compositing, as the input image 40 through user input or selection. .

The processor 220 can detect the face area through face detection technology using deep learning DLIB (distribution library), etc., and detects the feature value and style area for the face area through a deep learning engine such as ArcFace. Feature values can be extracted (S310). In detail, the processor 220 detects a face area in the first source image 510 and then extracts a face feature (hereinafter referred to as 'first face feature') 511 from the face area through a feature decomposition process. and a style feature (hereinafter referred to as 'first style feature') 512 can be extracted from the remaining area, the style area. It is assumed that other features except the face feature can be styles. Likewise, the processor 220 detects the face area in the second source image 520, extracts face features (hereinafter referred to as 'second face features') 521 from the face area through feature decomposition, and extracts the remaining area. A style feature (hereinafter referred to as a 'second style feature') 522 can be extracted from the in-style area.

The processor 220 extracts the first facial features 511 and the second source image 520 extracted from the first source image 510 according to a ratio set by default or user settings through deepfake technology such as simple swap. The synthetic face features 531 can be created by mixing the second face features 521 (S320).

The processor 220 creates the resulting image 530 by attaching the synthetic face feature 531 to the face area of the target image 450 while maintaining the style area of the target image 450 set as the style source. Can be created (S330). The processor 220 can generate the image 530 as a result of changing the face area of the target image 450 to the third face area while maintaining the style of the target image 450 through feature recombination. there is.

At this time, it is assumed that the first source image 510 among the first source image 510 and the second source image 520 is selected as the target image 450. The resulting image 530 can be created by attaching the synthetic facial feature 531 to the first source image 510 selected as the target image 450.

Additionally, the processor 220 may enhance the resolution of the resulting image 530 (S331). The processor 220 may output the resulting image 530 as a high-definition image through an image enhancement deep learning engine (eg, GAN Prior Embedded Network (GPEN), etc.).

Figures 6 and 7 show an example of an image synthesis process using a face filter according to an embodiment of the present invention.

Referring to FIGS. 6 and 7, the processor 220 can select a face filter 70 from the filter DB according to a user request, and selects the face feature (i.e., hidden face feature) 701 of the selected filter 70. A new result image 540 can be generated by recombining the synthetic face features 531 (S340).

The resynthesis process (S340) using the face filter 70 is the same or similar to the face swap process (S320) and the face attaching process (S330) described above. As shown in FIG. 7, the processor 220 can generate a third synthetic face feature 731 by mixing the synthetic face feature 531 and the hidden face feature 701 through face swap. The processor 220 attaches the third synthetic facial feature 731 to the face area of the first source image 510 while maintaining the style area of the first source image 510 selected as the target image 450. A new result image 540 may be created.

In these embodiments, the resulting image according to face synthesis can be diversified by using a face filter 70 with facial features other than the facial features included in the source image.

Figure 8 shows an example of a face synthesis service screen in one embodiment of the present invention.

Referring to FIG. 8, the face synthesis service screen 800 includes a source selection interface 810 for selecting a source image, a synthesis result interface 820 for providing a synthesis result image, and a synthesis result interface 820 for adjusting the synthesis ratio of the source image. It may include a ratio adjustment interface 830, a reset interface 840 for resetting the composite ratio of the source image, and a style selection interface 850 for selecting a style source (target image).

The user can upload the A image and B image of the target for compositing through the source selection interface 810.

The user can use the ratio adjustment interface 830 to adjust the composite ratio between the A image and the B image as desired. When the reset interface 840 is input, the composite ratio on the ratio adjustment interface 830 is automatically adjusted to the initial value (eg, 50:50).

The processor 220 can combine the A image and B image input as the source image at a ratio desired by the user. In this case, the source image selected as the A image can be applied as the style source. Through the style selection interface 850, one of image A and image B or another separate image can be selected and applied as a style source.

When the composite image of image A and image B is called the source image and the style image is the target image, you can change only the background image while maintaining the facial features of the source image by setting the weight at a ratio of 0:100=target:source. .

The processor 220 may display a composite result image using the A image and the B image through the composite result interface 820.

Furthermore, the face synthesis service screen 800 may further include a filter selection interface 860 for selecting a face filter, and a filter release interface 870 for canceling the face filter.

The filter selection interface 860 is in the form of an interface that selects face filters included in the filter DB one by one in a certain order or at random, as well as an interface that provides a list of face filters and selects a face filter through the list. It can be implemented.

The processor 220 may reflect the user's preference for face filters when selecting or providing a list of face filters in order through the filter selection interface 860. In other words, among the face filters included in the filter DB, the user's preferred face filter may be selected or sorted preferentially.

The processor 220 may display the composite result image to which the face filter selected through the filter selection interface 860 is applied through the composite result interface 820. Whenever the face filter is changed through the filter selection interface 860, a composite result image to which the changed face filter is applied can be displayed on the composite result interface 820.

When the filter release interface 870 is input, the application of the face filter may be canceled and the composite result image before the face filter is applied may be displayed on the composite result interface 820.

Figure 9 shows an example of a face synthesis result according to an embodiment of the present invention.

Referring to FIG. 9, when an A image and a B image are given as source images, the processor 220 mixes the facial features extracted from the A image and the facial features extracted from the B image to create C, which is the result of combining the A image and the B image. You can create images.

Since the C image is created by synthesizing only the facial features included in the source image, it has the limitation of not being able to resemble the face of the source image.

In this embodiment, a face filter can be used to create results that vary from lookalikes.

Figure 10 shows an example of the result of face synthesis using a face filter in one embodiment of the present invention.

Referring to FIG. 10, the processor 220 may resynthesize the F face feature of the face filter selected according to the user's request from the filter DB into the synthesis result of the A image and the B image to create a new synthesis result, image C'.

In other words, the processor 220 can create a third new person by adding the F facial feature unrelated to the source image to the result of combining the A image and the B image.

The processor 220 can use a face filter with an image effect that emphasizes facial features to diversify the deep learning face synthesis results compared to using only the source image.

In this way, according to embodiments of the present invention, in the process of face synthesis using a deep learning model, new results are provided by applying hidden face features to the result of face synthesis using source images, thereby improving service quality and user experience through diversification of face synthesis. can be improved.

The device described above may be implemented with hardware components, software components, and/or a combination of hardware components and software components. For example, the devices and components described in the embodiments include a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), and a programmable logic unit (PLU). It may be implemented using one or more general-purpose or special-purpose computers, such as a logic unit, microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. The software and/or data may be embodied in any type of machine, component, physical device, computer storage medium or device for the purpose of being interpreted by or providing instructions or data to the processing device. there is. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. At this time, the medium may continuously store a computer-executable program, or temporarily store it for execution or download. In addition, the medium may be a variety of recording or storage means in the form of a single or several pieces of hardware combined. It is not limited to a medium directly connected to a computer system and may be distributed over a network. Examples of media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, And there may be something configured to store program instructions, including ROM, RAM, flash memory, etc. Additionally, examples of other media include recording or storage media managed by app stores that distribute applications, sites or servers that supply or distribute various other software, etc.

As described above, although the embodiments have been described with limited examples and drawings, various modifications and variations can be made by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims (20)

In an image synthesis method executed on a computer device,
The computer device includes at least one processor configured to execute computer-readable instructions contained in a memory,
The image synthesis method is,
extracting a facial area from a first source image and a second source image, by the at least one processor;
combining, by the at least one processor, a face area extracted from the first source image and a face area extracted from the second source image;
generating a result image by combining the synthesized face area with a target image set as a style source, by the at least one processor; and
generating, by the at least one processor, a new result image by re-synthesizing a facial feature filter on the synthesized face area;
An image synthesis method including. According to paragraph 1,
The image synthesis method is,
Building a filter database consisting of a plurality of face feature filters by the at least one processor.
It further includes,
The step of generating the new result image is,
Re-synthesizing the facial feature filter selected from the filter database into the synthesized face area.
An image synthesis method including. According to paragraph 2,
The filter database consists of a plurality of face feature filters made up of different face features.
An image synthesis method characterized by . According to paragraph 2,
The face feature filter included in the filter database corresponds to an image effect filter in which face features corresponding to at least some elements included in the face area are enhanced.
An image synthesis method characterized by . According to paragraph 2,
The face feature filter included in the filter database includes at least one of an image effect filter consisting of human face features and an image effect filter consisting of animal face features.
An image synthesis method characterized by . According to paragraph 2,
The step of generating the new result image is,
Randomly selecting a facial feature filter from the filter database according to the user's request.
An image synthesis method including. According to paragraph 2,
The construction step is,
Determining user preference for face feature filters included in the filter database
Including,
The step of generating the new result image is,
Selecting a facial feature filter based on the user preference from the filter database according to the user's request.
An image synthesis method including. According to paragraph 1,
The target image corresponds to the image selected by the user among the first source image and the second source image.
An image synthesis method characterized by . According to paragraph 1,
The target image is an image different from the first source image or the second source image and corresponds to a separate image selected by the user.
An image synthesis method characterized by . According to paragraph 1,
The synthesis step is,
Creating a composite face area by mixing first facial features extracted from the face area of the first source image and second facial features extracted from the face area of the second source image at a ratio set by the user.
An image synthesis method including. A computer program stored in a computer-readable recording medium to cause the computer device to execute the image synthesis method of any one of claims 1 to 10. In computer devices,
At least one processor configured to execute computer readable instructions contained in memory
Including,
The at least one processor,
A process of extracting a face area from a first source image and a second source image;
A process of combining a face area extracted from the first source image and a face area extracted from the second source image;
A process of generating a result image by combining the synthesized face area with a target image set as a style source; and
A process of generating a new result image by recombining the facial feature filter into the synthesized face area.
A computer device that processes According to clause 12,
The at least one processor,
Build a filter database consisting of multiple face feature filters,
Re-synthesizing the facial feature filter selected from the filter database into the synthesized face region.
A computer device characterized by a. According to clause 13,
The filter database consists of a plurality of face feature filters made up of different face features.
A computer device characterized by a. According to clause 13,
The face feature filter included in the filter database corresponds to an image effect filter in which face features corresponding to at least some elements included in the face area are enhanced.
A computer device characterized by a. According to clause 13,
The face feature filter included in the filter database includes at least one of an image effect filter consisting of human face features and an image effect filter consisting of animal face features.
A computer device characterized by a. According to clause 13,
The at least one processor,
Selecting facial feature filters randomly from said filter database according to user's request
A computer device characterized by a. According to clause 13,
The at least one processor,
Identify user preferences for facial feature filters included in the filter database,
Selecting a facial feature filter based on the user preferences from the filter database upon user request.
A computer device characterized by a. According to clause 12,
The target image corresponds to an image selected by the user among the first source image and the second source image, or to a separate image selected by the user that is different from the first source image or the second source image. becoming
A computer device characterized by a. According to clause 12,
The at least one processor,
Generating a composite face area by mixing first facial features extracted from the face area of the first source image and second facial features extracted from the face area of the second source image at a ratio set by the user.
A computer device characterized by a.

Images