Search

KR-20260063626-A - METHOD AND SYSTEM FOR REGENERATING THUMBNAIL OF CONTENT OPTIMIZED FOR CONTENT EXPOSURE AREA OF SERVICE

KR20260063626AKR 20260063626 AKR20260063626 AKR 20260063626AKR-20260063626-A

Abstract

A method and system for generating a thumbnail of content optimized for a content exposure area of a service are disclosed. A thumbnail generation method according to one embodiment may include the steps of: classifying the image type of an image of content to be exposed through a service into one of a photo type and a non-photo type; classifying the type of a core subject for the photo type image into one of a person type, an object type, and a type where the core subject is not present; extracting an essential inclusion area in the image according to the image type and the type of the core subject; and generating a thumbnail of the content from the image based on the essential inclusion area.

Inventors

  • 최성재
  • 강재욱
  • 강승길
  • 박동주
  • 권혜나
  • 김지혜
  • 박보연

Assignees

  • 네이버 주식회사

Dates

Publication Date
20260507
Application Date
20241030

Claims (19)

  1. A thumbnail generation method of a thumbnail generation system implemented by at least one computer device, The above at least one computer device includes at least one processor, and The above thumbnail generation method is, A step of classifying the image type of an image of content to be exposed through a service into one of a photo type and a non-photo type by the above-mentioned at least one processor; A step of classifying the type of core subject for an image of the photograph type into one of a person type, an object type, and a type where the core subject is not present, by the above at least one processor; A step of extracting an essential inclusion area in the image according to the image type of the image and the type of the core subject by the at least one processor; and A step of generating a thumbnail of the content from the image based on the essential inclusion area by the at least one processor. A thumbnail generation method including
  2. In paragraph 1, The above photo types include a portrait photo type representing a photo containing a human face, an object photo type representing a photo containing an object but not a human face, and other photo types representing a photo among the above photo types excluding the photo of the portrait photo type and the photo of the object photo type. The above non-photographic type includes a visual data image type representing an image in which text is overlaid or which includes a table or chart, and other image types representing an image among the images of the above non-photographic type excluding the image of the visual data image type. A thumbnail generation method characterized by
  3. In paragraph 2, The step of classifying the above image types is, A thumbnail generation method characterized by classifying the image type of the above image into one of the above person photo type, the above object photo type, the above other photo type, the above visual data image type, and the above other image type.
  4. In paragraph 3, The step of extracting the essential inclusion area in the above image is, A thumbnail generation method characterized by extracting the essential inclusion area in the image such that the entire face of the person, which is the core subject, is included, when the image type is the person photo type and the core subject type is the person type.
  5. In paragraph 3, The step of extracting the essential inclusion area in the above image is, If the above image type is the above portrait photo type and the above core subject type is the above object type, the above first essential inclusion area is extracted to include the object which is the above core subject, and The step of generating a thumbnail of the above content is, Generating a first thumbnail based on the first required inclusion area, wherein if the first thumbnail includes a part of a person's face, the first thumbnail is adjusted so that the entire face of the person is included. A thumbnail generation method characterized by
  6. In paragraph 3, The step of extracting the essential inclusion area in the above image is, A thumbnail generation method characterized by, when the image type is the object photo type and the core subject type is the object type, extracting the essential inclusion area to include the object which is the core subject, and when there are two or more core subjects, extracting the essential inclusion area based on the size of the object detected in the image and the maximum utilization ratio of a preset blur.
  7. In paragraph 3, The step of extracting the essential inclusion area in the above image is, A thumbnail generation method characterized by extracting the required inclusion area based on a score for object detection and the number of subjects included when the type of the core subject is a type where the core subject is non-existent.
  8. In paragraph 1, The step of classifying the types of the above-mentioned core subjects is, A thumbnail generation method characterized by classifying the type of the core subject into one of a person type, an object type, and a core subject non-existence type using the title of the above content.
  9. In paragraph 1, The step of classifying the types of the above-mentioned core subjects is, A thumbnail generation method characterized by classifying the type of the core subject based on whether the title of the content includes a person's name, whether the title includes an object's name, and whether an object detected in the image corresponds to the person's name or the object's name.
  10. In Paragraph 9, The step of classifying the types of the above-mentioned core subjects is, A thumbnail generation method characterized by classifying the type of the core subject based further on whether a face is detected in the above image.
  11. In paragraph 1, The step of generating a thumbnail of the above content is, A thumbnail generation method characterized by resizing the size of the image or the essential inclusion area based on the ratio between the width and height of the image.
  12. In paragraph 1, The step of generating a thumbnail of the above content is, A thumbnail generation method characterized by resizing the required inclusion area to a size closest to the size of the image within a preset size of the thumbnail, wherein the resizing is performed by changing the position of the required inclusion area or adding margin to the image.
  13. A computer program stored on a computer-readable recording medium to be combined with a computer device to execute the method of any one of claims 1 to 12 on the computer device.
  14. In a thumbnail generation system implemented by at least one computer device, The above at least one computer device includes at least one processor implemented to execute computer-readable instructions, and By the above at least one processor, Classify the image type of the content images to be exposed through the service into one of photo type and non-photo type, and Classify the type of core subject for the above-mentioned photographic image into one of the following: person type, object type, and type where the core subject is absent. Based on the image type of the above image and the type of the above core subject, an essential inclusion area in the above image is extracted, and Generating a thumbnail of the content from the image based on the above-mentioned required inclusion area A thumbnail generation system featuring
  15. In Paragraph 14, The above photo types include a portrait photo type representing a photo containing a human face, an object photo type representing a photo containing an object but not a human face, and other photo types representing a photo among the above photo types excluding the photo of the portrait photo type and the photo of the object photo type. The above non-photographic type includes a visual data image type representing an image in which text is overlaid or which includes a table or chart, and other image types representing an image among the images of the above non-photographic type excluding the image of the visual data image type. A thumbnail generation system featuring
  16. In paragraph 15, To classify the above image types, by the above at least one processor, Classifying the image type of the above image into one of the above portrait type, the above object photo type, the above other photo type, the above visual data image type, and the above other image type. A thumbnail generation system featuring
  17. In Paragraph 14, In order to classify the types of the above-mentioned core subjects, by the above-mentioned at least one processor, Classifying the type of core subject into one of the following using the title of the above content: person type, object type, and non-existent core subject type. A thumbnail generation system featuring
  18. In Paragraph 14, In order to classify the types of the above-mentioned core subjects, by the above-mentioned at least one processor, Classifying the type of the core subject based on whether the title of the above content includes a person's name, whether the title includes an object's name, and whether an object detected in the above image corresponds to the person's name or the object's name. A thumbnail generation system featuring
  19. In Paragraph 14, To generate a thumbnail of the above content, by the at least one processor, Resizing the size of the image or the required inclusion area based on the ratio between the width and height of the image, or resizing the required inclusion area to a size closest to the size of the image within the preset size of the thumbnail, while changing the position of the required inclusion area or resizing by adding margins to the image. A thumbnail generation system featuring

Description

Method and System for Regenerating Thumbnail of Content Optimized for Content Exposure Area of Service The following description relates to a method and system for generating thumbnails of content optimized for the content display area of a service. Content displayed online includes a title and a thumbnail, and users select content based on these titles and thumbnails. Meanwhile, technology exists to automatically generate thumbnails using images included in the content. [Prior Art No.] Korean Patent Publication No. 10-2023-0172061 FIG. 1 is a drawing illustrating an example of a network environment according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating an example of a computer device according to an embodiment of the present invention. FIG. 3 is a drawing illustrating an example of a thumbnail generation system according to an embodiment of the present invention. FIG. 4 is a diagram illustrating an example of a process for generating a thumbnail in an embodiment of the present invention. FIG. 5 is a diagram illustrating an example of image preprocessing in an embodiment of the present invention. FIG. 6 is a diagram illustrating an example of an image type classification process in an embodiment of the present invention. FIG. 7 is a diagram illustrating an example of core subject classification in one embodiment of the present invention. FIG. 8 is a diagram illustrating an example of a patch selection process in an embodiment of the present invention. FIG. 9 is a drawing illustrating an example of a thumbnail generated according to the application of a thumbnail generation method according to an embodiment of the present invention. FIG. 10 is a flowchart illustrating an example of a thumbnail generation method according to an embodiment of the present invention. Hereinafter, embodiments will be described in detail with reference to the attached drawings. A thumbnail generation system according to embodiments of the present invention may be implemented by at least one computer device. In this case, a computer program according to one embodiment of the present invention may be installed and run on the computer device, and the computer device may perform a thumbnail generation method according to embodiments of the present invention under the control of the run computer program. The above-described computer program may be stored on a computer-readable recording medium to be combined with the computer device to execute the thumbnail generation method on the computer. FIG. 1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention. The network environment of FIG. 1 illustrates an example including a plurality of electronic devices (110, 120, 130, 140), a plurality of servers (150, 160), and a network (170). FIG. 1 is an example for explaining the invention, and the number of electronic devices or servers is not limited to that shown in FIG. 1. Furthermore, the network environment of FIG. 1 is merely an example of one of the environments applicable to the present embodiments, and the environments applicable to the present embodiments are not limited to the network environment of FIG. 1. Multiple electronic devices (110, 120, 130, 140) may be fixed terminals or mobile terminals implemented as computer devices. Examples of multiple electronic devices (110, 120, 130, 140) include smartphones, mobile phones, navigation systems, computers, laptops, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, etc. For example, FIG. 1 shows the shape of a smartphone as an example of an electronic device (110), but in embodiments of the present invention, the electronic device (110) may substantially refer to one of various physical computer devices capable of communicating with other electronic devices (120, 130, 140) and/or servers (150, 160) via a network (170) using a wireless or wired communication method. The communication method is not limited and may include not only communication methods utilizing communication networks (e.g., mobile communication networks, wired internet, wireless internet, broadcasting networks) that the network (170) may include, but also short-range wireless communication between devices. For example, the network (170) may include any one or more networks such as a PAN (personal area network), LAN (local area network), CAN (campus area network), MAN (metropolitan area network), WAN (wide area network), BBN (broadband network), and the Internet. Additionally, the network (170) may include any one or more network topologies such as a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or hierarchical network, but is not limited thereto. Each of the servers (150, 160) may be implemented as a computer device or multiple computer devices that communicate with multiple electronic devices (110, 120, 130, 140) through