Automatic positioning of textual content within digital images

Patent metadata

Field	Value
Publication number	US-11270485-B2
Application number	US-201916518433-A
Country	US
Kind code	B2
Filing date	Jul 22, 2019
Priority date	Jul 22, 2019
Publication date	Mar 8, 2022
Grant date	Mar 8, 2022

Abstract

Automatic positioning of textual content within digital images is leveraged in a digital medium environment. Initially, user input is received to add textual content to a digital image. A salient portion and a non-salient portion of the digital image are identified. The salient portion of the digital image contains a salient object which corresponds to the most important or noticeable object in a digital image, as opposed to non-salient objects which correspond to less important background objects or portions of an image. A placement region for the textual content within the non-salient portion of the digital image is automatically determined, and the digital image is modified by positioning the textual content within the automatically determined placement region of the digital image. Positioning the textual content may include automatically adjusting the textual content to fit within the placement region, such as by automatically scaling or aligning the textual content.

First claim

What is claimed is:

1. In a digital medium environment, a method for automatically positioning textural content within a digital image, the method comprising:
obtaining, by at least one computing device, the digital image;
receiving, by the at least one computing device, user input to add textual content to the digital image, wherein the user input does not specify a position to place the textual content within the digital image;
identifying, by the at least one computing device, a salient portion and a non-salient portion within the digital image, wherein the salient portion within the digital image contains a salient object of the digital image, wherein the salient object is an object of primary focus in the digital image;
automatically determining, by the at least one computing device, a placement region for the textual content within the non-salient portion of the digital image by:
determining candidate placement regions within the non-salient portion of the digital image;
calculating a placement score for each of the candidate placement regions within the non-salient portion of the digital image, wherein the placement score is calculated for each of the candidate placement regions based on a size of the respective candidate placement region and a proximity of the respective candidate placement region to the salient object; and
selecting the placement region from the candidate placement regions based on the placement region having a highest calculated placement score of the candidate placement regions;

modifying, by the at least one computing device, the digital image by positioning the textual content within the automatically determined placement region and scaling the textual content to fit within the automatically determined placement region; and
outputting, by the at least one computing device, the modified digital image for display.

2. A method as described in claim 1 , wherein the scaling the textual content to fit within the automatically determined placement region further comprises adjusting a font size of the textual content to fit within the automatically determined placement region.

3. A method as described in claim 1 , wherein the scaling the textual content to fit within the placement region comprises at least one of:
adjusting a font size of the textual content;
adjusting a font type of the textual content;
adjusting spacing between individual characters of the textual content; or
aligning the textual content within the placement region.

4. A method as described in claim 1 , wherein the modifying the digital image causes the textual content to be positioned within the placement region such that the salient object of the digital image is not obstructed by the textual content.

5. A method as described in claim 1 , wherein the placement region corresponds to a non-centered portion of the digital image.

6. A method as described in claim 1 , wherein the placement region for the textual content is automatically determined without receiving additional user input to specify a size or position of the textual content within the digital image.

7. The method as described in claim 1 , further comprising:
receiving, by the at least one computing device, additional user input to add additional textual content to the digital image;
automatically determining, by the at least one computing device, an additional placement region for the additional textual content within the digital image; and
modifying, by the at least one computing device, the digital image by positioning the textual content within the additional placement region while maintaining the textual content within the placement region of the digital image.

8. The method as described in claim 1 , further comprising:
receiving, by the at least one computing device, additional user input to adjust a view of the modified digital image with the textual content;
identifying, by the at least one computing device, a new salient portion and a new non-salient portion of the adjusted digital image;
automatically determining, by the at least one computing device, a new placement region for the textual content within the new non-salient portion of the digital image; and
modifying, by the at least one computing device, the adjusted digital image by repositioning the textual content within the new placement region of the new-salient portion of the adjusted digital image.

9. A text positioning system comprising:
an image saliency module implemented at least partially in hardware of at least one computing device to generate a saliency mask that defines a salient portion and a non-salient portion within a digital image, wherein the salient portion within the digital image contains a salient object of the digital image, wherein the salient object is an object of primary focus in the digital image;
a placement module implemented at least partially in hardware of the at least one computing device to determine candidate placement regions within the non-salient portion of the digital image based on the saliency mask;
a scoring module implemented at least partially in hardware of the at least one computing device to calculate a placement score for each of the candidate placement regions within the non-salient portion of the digital image, wherein the placement score is calculated for each of the candidate placement regions based on a size of the respective candidate placement region and a proximity of the respective candidate placement region to the salient object; and
a mapping module implemented at least partially in hardware of the at least one computing device to select a placement region from the candidate placement regions based on the placement region having a highest calculated placement score of the candidate placement regions, and to modify the digital image by positioning textual content within the selected placement region and automatically scaling the textual content to fit within the selected placement region.

10. The system of claim 9 , wherein the mapping module is further configured to automatically scale the textual content to fit within the selected placement region by adjusting a font size of the textual content.

11. The system of claim 9 , wherein the mapping module is configured to automatically scale the textual content to fit within the placement region by:
adjusting a font size of the textual content;
adjusting a font type of the textual content;
adjusting spacing between individual characters of the textual content; or
aligning the textual content within the placement region.

12. The system of claim 9 , wherein the mapping module modifies the digital image to cause the textual content to be positioned within the placement region such that the salient object of the digital image is not obstructed by the textual content.

13. The system of claim 9 , wherein the placement region corresponds to a non-centered portion of the digital image.

14. The system of claim 9 , wherein the placement region for the textual content is automatically selected without receiving additional user input to specify a size or position of the textual content within the digital image.

15. In a digital medium environment, a method for automatically positioning textual content within a digital image, the method comprising:
generating, by at least one computing device, a saliency mask that defines a salient portion and a non-salient portion within the digital image, wherein the salient portion within the digital image contains a salient object of the digital image, wherein the salient object is an object of primary focus in the digital image;
determinin

Assignees

• Adobe Inc

Inventors

• Sharma Mrinal Kumar
• Singhal Gourav

Classifications

• G06F40/166 Primary

  Editing, e.g. inserting or deleting · CPC title

• G06V10/462

  Salient features, e.g. scale invariant feature transforms [SIFT] · CPC title

• G06T11/60 Primary

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

• G06F40/103

  Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191) · CPC title

• G06V30/414

  Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text · CPC title