Intelligent context-based image recommendations

Patent metadata

Field	Value
Publication number	US-11238628-B2
Application number	US-201816113529-A
Country	US
Kind code	B2
Filing date	Aug 27, 2018
Priority date	Aug 27, 2018
Publication date	Feb 1, 2022
Grant date	Feb 1, 2022

Abstract

Methods and systems are provided for an intelligent auto-fill process capable of smartly filling objects on a canvas using selected context-based images. Content related to the canvas is analyzed to determine context tags related to the canvas. The context tags are used to generate a media list comprised of one or more context-based image. The media list is used to automatically fill at least one object on the canvas such that a relevant part of the context-based image is visible. In this way, objects on a canvas can be automatically filled with images related to the context of the canvas.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving an indication to auto-fill an object on a canvas, wherein the object has a predefined boundary utilized to fill the object with one or more images;
analyzing a background image of the canvas to determine a context of the canvas;
determining a set of ranked tags from the context of the canvas;
identifying, based on the set of ranked tags from the context of the canvas, an image to fill the object; and
filling the object with the image within the predefined boundary of the object.

2. The computer-implemented method of claim 1 , wherein the context of the canvas is further based on analyzing one or more of text associated with the canvas and a user-input word related to the canvas.

3. The computer-implemented method of claim 1 , the determining the context for the canvas further comprising:
retrieving a first set of tags related to a user-input word related to the canvas, wherein the first set of tags comprises a face tag, a place tag, or another tag.

4. The computer-implemented method of claim 3 , further comprising:
retrieving a second set of tags related to a background of the canvas, wherein the second set of tags comprises a background tag, or another face tag; and
identifying the set of ranked tags based on respective tag category weights associated with the first set of tags and the second set of tags.

5. The computer-implemented method of claim 1 , wherein receiving the indication to auto-fill the object on the canvas comprises receiving a set of text characters and a selection to auto-fill the text characters.

6. The computer-implemented method of claim 1 , wherein receiving the indication to auto-fill the object on the canvas comprises receiving a selection of a portion of the object within the predefined boundary.

7. The computer-implemented method of claim 1 , wherein the predefined boundary outlines the object on the canvas without user interaction to define the predefined boundary.

8. The computer-implemented method of claim 1 , wherein filling the object further comprises placing the image into the object such that a relevant area of the image is visible.

9. A non-transitory computer-readable storage medium including instructions which, when executed by a computer, cause the computer to perform operations comprising:
receiving an indication to auto-fill an object on a canvas;
based on a background image of the canvas and a user-input word related to the canvas, determining a set of ranked tags of a context for the canvas;
selecting, based on the set of ranked tags of the context, a plurality of images; and
filling the object using an image of the plurality of images.

10. The non-transitory computer-readable storage medium of claim 9 , further comprising:
retrieving a first set of tags related to the user-input word related to the canvas, wherein the first set of tags comprises a face tag, a place tag, or another tag; and
retrieving a second set of tags related to a background of the canvas, wherein the first set of tags comprises a background tag or another face tag.

11. The non-transitory computer-readable storage medium of claim 10 , further comprising:
identifying the set of ranked tags based on respective tag category weights associated with the first set of tags and the second set of tags.

12. The non-transitory computer-readable storage medium of claim 9 , wherein the context for the canvas comprises a predefined number of tags related to the canvas.

13. The non-transitory computer-readable storage medium of claim 9 , wherein filling the object further comprises:
placing the image into the object such that a relevant area of the image is visible.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the relevant area is a face, the face being placed at a center of a bounding box associated with the object.

15. The non-transitory computer-readable storage medium of claim 13 , wherein the relevant area is a place, a tagged portion of the image related to the place being placed at a center of a bounding box associated with the object.

16. A non-transitory computer-readable storage medium including instructions which, when executed by a computer, cause the computer to perform operations comprising:
receiving an indication to auto-fill an object on a canvas, wherein the object has a predefined boundary utilized to fill the object with one or more images;
analyzing a background image of the canvas to determine a context of the canvas;
determining a set of ranked tags from the context of the canvas;
identifying, based on the set of ranked tags from the context of the canvas, an image to fill the object; and
filling the object with the image within the predefined boundary of the object.

17. The non-transitory computer-readable storage medium of claim 16 , further comprising:
placing the image into the object such that a relevant area of the image is visible.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the relevant area comprises a face, the face being placed at a center of a bounding box associated with the object.

19. The non-transitory computer-readable storage medium of claim 17 , wherein the relevant area is not a face, the image being centered in a bounding box associated with the object.

20. The non-transitory computer-readable storage medium of claim 17 , wherein the context of the canvas comprises a background of the canvas or a user-input word related to the canvas.

Assignees

• Adobe Inc

Inventors

• Mehta Saurabh
• Gupta Saurabh
• Bhatt Sameer

Classifications

• G06F16/24578

  using ranking · CPC title

• G06T2200/24

  involving graphical user interfaces [GUIs] · CPC title

• G06T11/60 Primary

  Creating or editing images; Combining images with text · CPC title

• G06F16/5866

  using information manually generated, e.g. tags, keywords, comments, manually generated location and time information · CPC title

• G06F3/04842

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title