Search

KR-20260064140-A - Method and device for processing images based on artificial intelligence

KR20260064140AKR 20260064140 AKR20260064140 AKR 20260064140AKR-20260064140-A

Abstract

A method for processing an image based on artificial intelligence may include: a step of determining the state of at least one processing result output from an input image through a first artificial neural network model trained to perform at least one processing on an input image; a step of training a second artificial neural network model to determine the location of at least one partial image to be cropped from an input image according to the purpose of the processing, by learning the state information of at least one processed result so that the success probability of at least one processing is greater than a certain level; and a step of cropping an input image into at least one partial image through the second artificial neural network model, inputting each partial image into the first artificial neural network model, and performing at least one processing.

Inventors

  • 이호준

Assignees

  • 주식회사 엑스퍼티

Dates

Publication Date
20260507
Application Date
20241031

Claims (10)

  1. As a method for processing images based on artificial intelligence, A step of determining the state of at least one processing result output from an input image through a first artificial neural network model trained to perform at least one processing on an input image; A step of training a second artificial neural network model to determine the location of at least one partial image to be cropped in an input image according to the purpose of processing, by learning state information of at least one processed result so that the success probability of at least one processing is greater than a certain level; and A step comprising cropping an input image into at least one partial image through the second artificial neural network model, inputting each partial image into the first artificial neural network model, and performing at least one processing step. Method for processing images.
  2. In paragraph 1, The above at least one processing step is, Characterized by including a process of recognizing a text area containing a first text in an input image and removing the text area from the image. Method for processing images.
  3. In paragraph 2, The above at least one processing step is, Characterized by further including an inpainting process for the empty area resulting from the removal of the text area, so as to match the surrounding area of the empty area. Method for processing images.
  4. In paragraph 3, The above inpainting process is characterized by being processed by referring to at least one image information of another location within the input image associated with the above empty area. Method for processing images.
  5. In paragraph 3, The above at least one processing step is, Characterized by further including a process of placing a second text, translated from the first text into a target language, at a position corresponding to the text area. Method for processing images.
  6. In paragraph 5, The arrangement of the second text is characterized by taking into account the shape of the second text, such that the second text covers part or all of the inpainted area. Method for processing images.
  7. In paragraph 6, The arrangement of the second text above is characterized by being arranged to selectively obscure parts with low reliability when performing inpainting processing through the first artificial neural network model. Method for processing images.
  8. In paragraph 5, The above second text is characterized by being placed with the image effect of the above first text applied. Method for processing images.
  9. In paragraph 2, A method for processing an image, further comprising the step of determining a position to be cropped in the input image based on the size of the first text when cropping the input image into at least one partial image.
  10. In paragraph 1, A method for processing an image, characterized in that the input image is a webtoon image.

Description

Method and device for processing images based on artificial intelligence Various embodiments of the present disclosure relate to methods and apparatus for processing images based on artificial intelligence. Webtoons are digital comics primarily serialized on online platforms, encompassing a wide variety of genres and styles. Generally, webtoons are presented as a single image in a vertical scrolling format. They are optimized for easy reading on mobile devices, and each episode features a continuous narrative progression. The webtoon market has grown rapidly in recent years due to the increase in digital content consumption and globalization, and is gaining popularity in various regions including Korea, Asia, North America, and Europe. Thanks to the development of various platforms and genres, readers now have a wider range of choices, and webtoons have the potential to create synergy through linkages with other media such as animation, drama, and movies. In order to provide webtoons to readers in various regions, a method has mainly been used in which content providers manually translate the text of the content through professional translators, modify the content by overlaying the translated text onto the original image, and then distribute it. These conventional manual methods required significant investment in terms of time and cost; therefore, recently, methods that recognize speech bubbles in original images and automatically translate the text within them are primarily being used. Recently, technology for automatically translating text within webtoon images by recognizing it has been developed. However, since the text within webtoon images is digitized, manual tasks such as recognizing the text and removing the corresponding text areas had to be performed separately. Therefore, technology is needed to recognize text in webtoon images, remove the recognized text area to naturally fill that part, and translate the recognized text to insert it at the original text location. FIG. 1 is a diagram illustrating an artificial intelligence-based image processing according to an embodiment of the present invention. FIG. 2 is a drawing illustrating an artificial intelligence-based image processing device according to one embodiment of the present invention. FIG. 3 is a diagram illustrating the function of artificial intelligence as an embodiment of the present invention. FIG. 4 is a diagram illustrating examples of artificial intelligence-based processing as an embodiment of the present invention. FIG. 5 is a diagram illustrating the state information of the result of image processing according to one embodiment of the present invention. FIG. 6 illustrates a flowchart of a method for processing an image according to one embodiment of the present invention. The embodiments described in this specification and the configurations illustrated in the drawings are merely preferred examples of the disclosed invention, and various modifications that may replace the embodiments and drawings of this specification may exist at the time of filing this application, and the same reference numerals or symbols presented in each of the drawings represent parts or components that perform substantially the same function. In addition, the suffix "~bu" for components used in the description of this specification is assigned or used interchangeably solely for the sake of ease of drafting the specification and does not inherently possess a distinct meaning or role. Furthermore, the "~bu" includes units realized by hardware, units realized by software, and units realized using both methods. Additionally, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware. In this specification, expressions such as "A and/or B", "at least one of A and B," etc. refer to all possible combinations of items listed together, and terms including ordinal numbers, such as first and second, etc., may be used to describe various components, but said components are not limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. Furthermore, in this specification, terms such as "comprising" and "may comprise" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and do not preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. Furthermore, the terms used in this specification are used merely to describe specific embodiments and are not intended to limit the scope of other embodiments. A singular expression may include a plural expression unless the context clearly indicates otherwise. All terms used herein, including technical or scientific terms, may have the same meaning as generally understood by those skilled in the art to which this disclosure applies. Terms defined in commonl