Techniques for incorporating a text-containing image into a digital image

• US 10,573,039 B2
• Filed: 10/03/2016
• Issued: 02/25/2020
• Est. Priority Date: 10/03/2016
• Status: Active Grant

• Current Assignee: Netflix, Inc.
• Original Assignee: Netflix, Inc.
• Inventors: Kansara, Apurvakumar Dilipkumar
• Primary Examiner(s): Misleh, Justin P.
• Application Number:
  US15/284,285
• Publication Number:
  US 20180096502A1
• Time in Patent Office: 1,240 Days
• Field of Search: None
• CPC Class Codes: G06Q 30/0276 Advertisement creation
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text

Abstract

One embodiment of the present invention sets forth a technique for incorporating a text-containing image into a digital. The technique includes analyzing a digital image to determine one or more text-allowed regions included in the digital image, and, for each of the one or more text-allowed regions, computing a numeric value based on a color contrast between pixels of a text-containing image and pixels of the text-allowed region, wherein the text-containing image is to be incorporated into one of the text-allowed regions included in the digital image. The technique further includes selecting a first text-allowed region based at least in part on the numeric value computed for each text-allowed region, and incorporating the text-containing image into the first text-allowed region included in the digital image.

Claims

1. A computer-implemented method, comprising:

analyzing a digital image to determine one or more text-allowed regions included in the digital image for a text-containing image, wherein the text-containing image has a first aspect ratio and a first shape, and the one or more text-allowed regions include a first text-allowed region having an aspect ratio equal to the first aspect ratio and a shape that is not equal to the first shape;

for each of the one or more text-allowed regions, computing a numeric value based on a color contrast between pixels of the text-containing image and pixels of the text-allowed region;

selecting the first text-allowed region based at least in part on the numeric value computed for each text-allowed region; and

incorporating the text-containing image into the first text-allowed region included in the digital image.

2. The method of claim 1, further comprising determining that the digital image does not include any text prior to analyzing the digital image to determine the one or more text-allowed regions.

3. The method of claim 1, wherein each of the one or more text-allowed regions comprises a region of the digital image that does not overlap a proscribed portion of the digital image.

4. The method of claim 3, wherein the proscribed portion of the digital image comprises at least one of a visually interesting region included in the digital image and a previously-defined reserved portion of the digital image.

5. The method of claim 4, wherein the reserved portion of the digital image comprises a portion of the digital image reserved for another text-containing image.

6. The method of claim 4, wherein the visually interesting region includes one or more edge pixels determined via one or more edge detection operations performed on the digital image.

7. The method of claim 4, wherein the visually interesting region comprises a portion of the digital image that includes a detected face.

8. The method of claim 1, wherein, for each of the one or more text-allowed regions, the color contrast is determined by computing a distance in color space between pixels in the text-containing image and pixels in the text-allowed region.

9. The method of claim 8, wherein the distance in color space is based on a color palette associated with the text-containing image and a color palette associated with the text-allowed region.

10. The method of claim 1, wherein each of the one or more text-allowed regions has an aspect ratio that is equal to the first aspect ratio of the text-containing image.

11. The method of claim 1, wherein computing the numeric value comprises computing the numeric value based on the color contrast between pixels of the text-containing image and a sub-portion of pixels of the text-allowed region, wherein the sub-portion of pixels comprises pixels of the text-allowed region that are adjacent to the text-containing image when the text-containing image is located within the text-allowed region.

12. The method of claim 1, wherein the one or more text-allowed regions further include a second text-allowed region having an aspect ratio equal to the first aspect ratio and a shape that is not equal to the first shape and is not equal to the shape of the first text-allowed region.

13. The method of claim 1, wherein the first text-allowed region comprises at least one of a circle shape, oval shape, polygon shape, or an irregular shape.

14. A non-transitory computer-readable storage medium including instructions that, when executed by a processor, cause the processor to perform the steps of:

receiving a request to translate an element of source text from an origin language;

performing one or more edge detection operations on a digital image to detect one or more edge pixels included in the digital image;

determining a negative space region included in the digital image that does not include any edge pixels;

defining one or more text-allowed regions within the negative space region for a text-containing image, wherein the text-containing image has a first aspect ratio and a first shape, and the one or more text-allowed regions include a first text-allowed region having an aspect ratio equal to the first aspect ratio and a shape that is not equal to the first shape;

for each of the one or more text-allowed regions, computing a numeric value based on a color contrast between pixels of the text-containing image and pixels of the text-allowed region;

selecting the first text-allowed region based at least in part on the numeric value computed for each text-allowed region; and

incorporating the text-containing image into the first text-allowed region included in the digital image.

15. The non-transitory computer-readable storage medium of claim 14, wherein the at least one text-allowed region has an area that is greater than a minimum threshold value.

16. The non-transitory computer-readable storage medium of claim 15, wherein the minimum threshold value is based on an area of the text-containing image.

17. The non-transitory computer-readable storage medium of claim 14, further comprising performing one or more blurring operations on the digital image prior to performing the one or more edge detection operations on the digital image.

18. The non-transitory computer-readable storage medium of claim 14, wherein the numeric value computed for each of the one or more text-allowed regions is further based on proximity of the one or more edge pixels included in the digital image to a proscribed portion of the digital image.

19. The non-transitory computer-readable storage medium of claim 18, further comprising determining that the digital image does not include any text prior to analyzing the digital image to determine the one or more text-allowed regions.

20. The non-transitory computer-readable storage medium of claim 18, wherein each of the one or more text-allowed regions comprises a region of the digital image that does not overlap a proscribed portion of the digital image.

21. The non-transitory computer-readable storage medium of claim 20, wherein the proscribed portion of the digital image comprises at least one of a visually interesting region included in the digital image and a previously-defined reserved portion of the digital image.

22. The non-transitory computer-readable storage medium of claim 21, wherein the reserved portion of the digital image comprises a portion of the digital image reserved for another text-containing image.

23. A system, comprising:

a memory storing a text-locating application; and

a processor that is coupled to the memory and, when executing the text-locating application, is configured to;

analyze a digital image to determine one or more text-allowed regions included in the digital image for a text-containing image, wherein the text-containing image has a first aspect ratio and a first shape, and the one or more text-allowed regions include a first text-allowed region having an aspect ratio equal to the first aspect ratio and a shape that is not equal to the first shape;

for each of the one or more text-allowed regions, computing a numeric value based on a color contrast between pixels of the text-containing image and pixels of the text-allowed region;

select the first text-allowed region based at least in part on the numeric value computed for each text-allowed region; and

incorporate the text-containing image into the first text-allowed region included in the digital image,

wherein each of the one or more text-allowed regions comprises a region of the digital image that does not overlap a proscribed portion of the digital image.

24. The system of claim 23, wherein analyzing the digital image to determine the one or more text-allowed regions comprises:

performing one or more edge detection operations on the digital image to detect one or more edge pixels included in the digital image;

determining a negative space region included in the digital image that does not include any edge pixels; and

defining at least one text-allowed region within the negative space region.