KR-20260062516-A - METHOD AND SYSTEM FOR PROVIDING IMAGE OF FUTURE BASED ON ARTIFICIAL INTELLIGENCE

Abstract

According to an embodiment of the present invention, a method for providing future appearance images based on artificial intelligence is provided, comprising the steps of: receiving a first image from a user terminal; separating an object from the first image; learning the first image from which the object has been separated; generating a plurality of second images in which a plurality of appearances by age are expressed by inputting a prompt to a model obtained as a learning result; and providing the plurality of second images to the user terminal.

Inventors

• 김대영

Assignees

• 김대영

Dates

Publication Date

20260507

Application Date

20241029

Claims (3)

1. As a method for a service server to provide a future appearance image based on artificial intelligence, A step of receiving a first image from a user terminal; A step of separating an object from the first image above; Step of learning a first image in which the object is separated; A step of generating multiple second images in which multiple age-specific appearances are expressed by inputting a prompt into a model obtained as a learning result; and AI-based future image providing method comprising the step of providing the plurality of second images to the user terminal.
2. In paragraph 1, The step of generating the plurality of second images above is performed using a stable diffusion algorithm, an AI-based method for providing future images.
3. In paragraph 1, A step of receiving user selection information among the plurality of second images from the user terminal; and A method for providing an AI-based future image, further comprising the step of providing a result to the user terminal to which post-correction has been applied to a second image selected by the user.

Description

Method and System for Providing Images of the Future Based on Artificial Intelligence The present invention relates to a method and system for providing future appearance images based on artificial intelligence, and more specifically, to a method and system for estimating future appearances by age based on input images and providing the estimated appearance as an image. A human face image contains a lot of information representing individual characteristics such as age and gender. Therefore, various Human-Computer Interaction (HCI) technologies, including user authentication, are being researched, developed, and used based on human facial images. For modern people, interest in appearance and beauty is gradually increasing, and consequently, there is a growing number of cases where people are curious about what they will look like at different ages in the future. In addition, in the fields of computer graphics and computer vision, technologies are being developed to model and analyze human faces to represent and generate faces according to desired conditions, or to recognize human faces. In particular, facial image transformation is becoming increasingly important due to its diverse applications. However, the basic structure of a person's face changes with age, and changes such as wrinkles occur due to skin aging. Furthermore, while there are aspects of facial changes due to age that are common across people, there are also areas where facial changes vary significantly from person to person. In the field of human face image recognition and transformation, technologies have been researched to generate human face images corresponding to a specific age by performing face image transformations based on changes in age on input human face images, reflecting the characteristics mentioned above. Existing image-based age transformation models apply age transformation using images categorized by group. These models have limitations, as they cannot accurately estimate the age of images transformed to a specific age and are restricted in their ability to be transformed to a specific age. FIG. 1 is a diagram schematically showing the configuration of an artificial intelligence-based future appearance image providing system according to one embodiment of the present invention. FIG. 2 is a block diagram illustrating the detailed operation and internal configuration of a service server according to an embodiment of the present invention. Figure 3 shows an example of a result provided to a user after estimating the appearance of a child at ages 5, 10, 15, and 20 and generating an image. The following detailed description of the invention refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that various embodiments of the invention are different but need not be mutually exclusive. For example, specific shapes, structures, and characteristics described herein with respect to one embodiment may be implemented in other embodiments without departing from the spirit and scope of the invention. It should also be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the following detailed description is not intended to be limiting, and the scope of the invention is limited only by the appended claims, including all equivalents to those claimed therein, provided appropriately described. Similar reference numerals in the drawings refer to the same or similar functions across various aspects. Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings in order to enable a person skilled in the art to easily practice the present invention. FIG. 1 is a diagram schematically showing the configuration of an artificial intelligence-based future appearance image providing system according to one embodiment of the present invention. Referring to FIG. 1, a system according to an embodiment of the present invention may be configured to include a plurality of user terminals (100) and a service server (200). A number of user terminals (100) and service servers (200) can communicate with each other through a communication network, for example, a mobile communication network, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), the World Wide Web (WWW), and a wireless communication network (WiFi). The user terminal (100) may be implemented in any form as long as it is a device capable of communicating with the outside and has a computing function. For example, it may be implemented as a smartphone, tablet PC, desktop, laptop, PDA, etc., but is not limited thereto. An application for receiving a service according