Search

KR-20260067276-A - ELECTRONIC DEVICE AND METHOD FOR PROCESSING IMAGE USING THE SAME

KR20260067276AKR 20260067276 AKR20260067276 AKR 20260067276AKR-20260067276-A

Abstract

An electronic device according to various embodiments of the present invention comprises a touch screen display, a first camera having a first characteristic and a second camera having a second characteristic, at least one processor, and a memory for storing instructions, wherein when the instructions are executed individually or collectively by the at least one processor, the electronic device acquires a first preview image through the first camera, receives user input for creating an object within the first preview image through the touch screen display, creates the object based on the user input through a generative artificial intelligence model trained to create at least one object based on text input, drawing input, or image input, displays the created object within the first preview image through the touch screen display, acquires a second preview image through the second camera based on confirmation that the first camera is switched to the second camera, corrects the object based on the second characteristic of the second camera, and through the touch screen display, the second preview The corrected object can be displayed within the image. Various other embodiments may be possible.

Inventors

  • 유형진
  • 김문수
  • 배창섭
  • 유정곤
  • 이성민
  • 정주영
  • 하대성

Assignees

  • 삼성전자주식회사

Dates

Publication Date
20260512
Application Date
20250214
Priority Date
20241105

Claims (20)

  1. In the electronic device (200), touch screen display (201); A first camera (212a) having a first characteristic and a second camera (212b) having a second characteristic; At least one processor (120); and It includes a memory (130) for storing instructions, When the above instructions are executed individually or collectively by the at least one processor (120), the electronic device (200), A first preview image (610) is obtained through the first camera (212a), and Through the touch screen display (201), user input for creating an object (611) within the first preview image (610) is received, and The object (611) based on the user input is generated through a generative artificial intelligence model (510) trained to generate at least one object based on text input, drawing input, or image input, and The generated object (611) is displayed within the first preview image (610) through the touch screen display (201), and Based on the confirmation that the first camera (212a) is switched to the second camera (212b), a second preview image (620) is obtained through the second camera (212b), and Correcting the object (611) based on the second characteristic of the second camera (212b), and An electronic device that displays the corrected object (621) within the second preview image (620) through the touch screen display (201).
  2. In Article 1, The first characteristic above includes at least one of the first brightness, first color tone, first position information, and first field of view of the first camera (212a), and The second characteristic includes at least one of the second brightness, second color tone, second position information, and second field of view of the second camera (212b), wherein The above first characteristic is an electronic device different from the above second characteristic.
  3. In Article 1, When the above instructions are executed individually or collectively by the at least one processor (120), the electronic device (200), An electronic device that stores the object (611) generated using the above generative artificial intelligence model (510) in the memory (130).
  4. In Article 1, It further includes at least one of an input module (150) and a microphone, and The above user input is an electronic device comprising at least one of text input, drawing input, and voice input.
  5. In Article 1, The above generative artificial intelligence model (510) is configured to generate a prompt based on the user input for generating the object image (611), and the generative artificial intelligence model (510) is an electronic device trained to generate the prompt based on at least one of text input, drawing input, and voice input.
  6. In Article 1, The above generative artificial intelligence model (510) is an electronic device included in at least one of the electronic device (200) and the server (108).
  7. In Article 1, An electronic device comprising at least one of zoom-in and zoom-out when the first camera (212a) is switched to the second camera (212b).
  8. In Article 1, When the above instructions are executed individually or collectively by the at least one processor (120), the electronic device (200), An electronic device that adjusts the size of the corrected object (621) to correspond to a change in the size of the second preview image (620) based on confirmation that the first camera (212a) is switched to the second camera (212b).
  9. In Article 1, When the above instructions are executed individually or collectively by the at least one processor (120), the electronic device (200), An electronic device that adjusts at least one of the brightness and color tone of the corrected object (621) to correspond to a change in at least one of the brightness and color tone of the second preview image (620), based on confirmation that the first camera (212a) is switched to the second camera (212b).
  10. In Article 1, When the above instructions are executed individually or collectively by the at least one processor (120), the electronic device (200), An electronic device that adjusts the position of the corrected object (621) to correspond to a position change of the second preview image (620) based on confirmation that the first camera (212a) is switched to the second camera (212b).
  11. In a method for processing an image using an electronic device (200), The operation of acquiring a first preview image (610) through a first camera (212a) having a first characteristic; The operation of receiving user input to create an object (611) within the first preview image (610) through a touch screen display (201); The operation of generating the object (611) based on the user input through a generative artificial intelligence model (510) trained to generate at least one object based on text input, drawing input, or image input; The operation of displaying the generated object (611) within the first preview image (610) through the touch screen display (201); An operation to check whether the first camera (212a) is switched to a second camera (212b) having a second characteristic; An operation of acquiring a second preview image (620) through the second camera (212b) based on confirmation that the first camera (212a) is switched to the second camera (212b); An operation to correct the object (611) based on the second characteristic of the second camera (212b); and A method including the operation of displaying the corrected object (621) in the second preview image (620) through the touch screen display (201).
  12. In Paragraph 11, The first characteristic above includes at least one of the first brightness, first color tone, first position information, and first field of view of the first camera (212a), and The second characteristic includes at least one of the second brightness, second color tone, second position information, and second field of view of the second camera (212b), wherein The above first characteristic is a method different from the above second characteristic.
  13. In Paragraph 11, A method further comprising the operation of storing the object (611) generated using the above-mentioned generative artificial intelligence model (510) in memory (130).
  14. In Paragraph 11, It further includes at least one of an input module (150) and a microphone, and The above user input is a method comprising at least one of text input, drawing input, and voice input.
  15. In Paragraph 11, A method in which the generative artificial intelligence model (510) further includes an operation of generating a prompt based on the user input for generating the object (611), wherein the generative artificial intelligence model (510) is trained to generate the prompt based on at least one of text input, drawing input, and voice input.
  16. In Paragraph 11, The above generative artificial intelligence model (510) is a method included in at least one of the electronic device (200) and server (108).
  17. In Paragraph 11, A method in which the first camera (212a) is switched to the second camera (212b), comprising at least one of zoom-in and zoom-out.
  18. In Paragraph 11, A method further comprising the operation of adjusting the size of the corrected object (621) to correspond to the size change of the second preview image (620) based on confirmation that the first camera (212a) is switched to the second camera (212b).
  19. In Paragraph 11, A method further comprising the operation of adjusting at least one of the brightness and color tone of the corrected object (621) to correspond to at least one of the change in brightness and color tone of the second preview image (620), based on confirmation that the first camera (212a) is switched to the second camera (212b).
  20. In Paragraph 11, A method further comprising the operation of adjusting the position of the corrected object image (621) to correspond to the position change of the second preview image (620) based on confirmation that the first camera (212a) is switched to the second camera (212b).

Description

ELECTRONIC DEVICE AND METHOD FOR PROCESSING IMAGE USING THE SAME Various embodiments of the present invention disclose an electronic device and a method for processing an image using said electronic device. The use of electronic devices such as bar-type, foldable-type, rollable-type, or sliding-type devices is increasing, and various functions are being provided to these devices. The above electronic device can acquire at least one of an image and a video using one or more cameras. The electronic device described above can provide a function to add and edit a new image (e.g., an object image or a virtual object) to at least one of the images and videos acquired using a camera. The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing may be applied as prior art in relation to the present disclosure. An electronic device can add new objects (e.g., object images or virtual objects) to a preview image acquired through a camera using generative artificial intelligence (AI) or a generative artificial intelligence model. For example, if an object (e.g., an object image or a virtual object) is added to a first preview image obtained through a first camera, and then the first camera is switched to a second camera, a difference (brightness, color tone, and/or position) may occur between the second preview image obtained through the second camera and the object. For example, when a user of an electronic device generates a new image by adding an object (e.g., object image or virtual object) to an original image (e.g., preview image) captured through a camera, if there is a difference (e.g., disparity) between the original image and the object image, the user may not be able to obtain the desired image. Various embodiments of the present invention may provide an electronic device capable of correcting an object (e.g., an object image or a virtual object) to correspond to the characteristics of the second camera (e.g., a second preview image) even when the first camera is switched to the second camera, and an image processing method using said electronic device. The technical problems to be solved in this disclosure are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the description below. An electronic device according to one embodiment of the present invention may include a touch screen display, a first camera having a first characteristic and a second camera having a second characteristic, at least one processor, and a memory for storing instructions. According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may acquire a first preview image through the first camera, receive user input to create an object within the first preview image through the touch screen display, create the object based on the user input through a generative artificial intelligence model trained to create at least one object based on text input, drawing input, or image input, display the created object within the first preview image through the touch screen display, acquire a second preview image through the second camera based on confirmation that the first camera is switched to the second camera, correct the object based on the second characteristic of the second camera, and display the corrected object within the second preview image through the touch screen display. A method for processing an image using an electronic device according to an embodiment of the present invention may include an operation of acquiring a first preview image through a first camera having a first characteristic. According to an embodiment, the method may include an operation of receiving user input for creating an object within the first preview image through a touch screen display. According to an embodiment, the method may include an operation of creating the object based on the user input through a generative artificial intelligence model trained to create at least one object based on text input, drawing input, or image input. According to an embodiment, the method may include an operation of displaying the created object within the first preview image through the touch screen display. According to an embodiment, the method may include an operation of checking whether the first camera is switched to a second camera having a second characteristic. According to an embodiment, the method may include an operation of acquiring a second preview image through the second camera based on the confirmation that the first camera is switched to the second camera. According to one embodiment, the method may include an operation of correcting the object based on the second characteristic of the second camera. According to one embodiment, the method may include an