IP Library Granted Patent US 10,796,416
Granted Patent B2
US 10,796,416 · App. 16/001,829 · Granted Oct 6, 2020

Recolored collage generation based on color hue distances

Inventors: Shailendra Singh Rathore (Jodhpur, IN); Anmol Dhawan (Ghaziabad, IN); Anant Jain (New Delhi, IN)
Assignee: ADOBE INC.
G06T5/005G06K9/4652G06K9/6223G06T5/50G06T11/60G06T2207/10024
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,796,416
App. No.
16/001,829
Granted
Oct 6, 2020
Kind
B2
Abstract

Certain embodiments involve generating recolored collages. For example, a method includes receiving a first image from and a second image. The method also includes grouping color hues within the first image into a first color hue cluster, and grouping color hues within the second image into a second color hue cluster. Further, the method includes determining that a first hue center of the first color hue cluster is within a distance range of a second hue center of the second color hue cluster. Additionally, the method includes generating a first recolored image by recoloring pixels of the first image having color hues outside the first color hue cluster and generating a second recolored image by recoloring pixels of the second image having color hues outside the second color hue cluster. Moreover, the method includes outputting a recolored collage including the first recolored image and the second recolored image.

Claims (63)

1. A method for modifying image content based on color information computed for a set of collage images, wherein the method includes one or more processing devices performing operations comprising:

receiving a first image from the set of collage images and a second image from the set of collage images;

grouping (i) a first set of color hues within the first image into a first color hue cluster and (ii) a second set of color hues within the second image into a second color hue cluster;

determining that a first hue center of the first color hue cluster is within a distance range of a second hue center of the second color hue cluster;

generating (i) a first recolored image by recoloring pixels of the first image having color hues outside the first color hue cluster and (ii) a second recolored image by recoloring pixels of the second image having color hues outside the second color hue cluster; and

outputting a recolored collage comprising the first recolored image and the second recolored image.

2. The method of claim 1 , the operations further comprising:

converting the set of collage images to a hue, saturation, lightness (HSL) color space; and

flattening the set of collage images in the HSL color space to remove saturation and lightness components.

3. The method of claim 1 , wherein the first color hue cluster, the second color hue cluster, the first hue center, and the second hue center are computed using a k-means clustering operation.

4. The method of claim 3 , wherein the k-means clustering operation comprises clustering the pixels of the first image into three different color hue clusters representing three ranges of color hues.

5. The method of claim 1 , comprising:

determining a collage layout grammar from a set of collage layout grammars that displays a largest portion of remaining original color hues located in the first recolored image and the second recolored image; and

placing the first recolored image and the second recolored image in the collage layout grammar.

6. The method of claim 1 , comprising:

identifying a salient area of the first image; and

grouping the color hues within the salient area of the first image into the first color hue cluster.

7. The method of claim 1 , comprising:

grouping (i) a third set of color hues within the first image into a third color hue cluster and (ii) a fourth set of color hues within the second image into a fourth color hue cluster;

determining that a third hue center of the third color hue cluster is within a distance range of a fourth hue center of the fourth color hue cluster;

generating (i) a third recolored image by recoloring the pixels of the first image having color hues outside the third color hue cluster and (ii) a fourth recolored image by recoloring the pixels of the second image having color hues outside the fourth color hue cluster; and

outputting an additional recolored collage comprising the third recolored image and the fourth recolored image, wherein the additional recolored collage comprises a smaller portion of remaining original color hues of the first image and the second image than the recolored collage.

8. The method of claim 1 , wherein the distance range comprises a 20 degree interval on a hue, saturation, lightness (HSL) color wheel.

9. A computing system comprising:

means for receiving a first image from a set of collage images and a second image from the set of collage images;

means for grouping (i) a first set of color hues within the first image into a first color hue cluster and (ii) a second set of color hues within the second image into a second color hue cluster;

means for determining that a first hue center of the first color hue cluster is within a distance range of a second hue center of the second color hue cluster;

means for generating (i) a first recolored image by recoloring pixels of the first image having color hues outside the first color hue cluster and (ii) a second recolored image by recoloring pixels of the second image having color hues outside the second color hue cluster; and

means for outputting a recolored collage comprising the first recolored image and the second recolored image.

10. The computing system of claim 9 , comprising:

means for converting the set of collage images to a hue, saturation, lightness (HSL) color space; and

means for flattening the set of collage images in the HSL color space to remove saturation and lightness components.

11. The computing system of claim 9 , wherein the first color hue cluster, the second color hue cluster, the first hue center, and the second hue center are computed using a k-means clustering operation, and wherein the k-means clustering operation comprises clustering the pixels of the first image into three different color hue clusters representing three ranges of color hues.

12. The computing system of claim 9 , comprising:

means for determining a collage layout grammar from a set of collage layout grammars that displays a largest portion of remaining original color hues located in the first recolored image and the second recolored image; and

means for placing the first recolored image and the second recolored image in the collage layout grammar.

13. The computing system of claim 9 , comprising:

means for identifying a salient area of the first image; and

means for grouping the color hues within the salient area of the first image into the first color hue cluster.

14. The computing system of claim 9 , comprising:

means for grouping (i) a third set of color hues within the first image into a third color hue cluster and (ii) a fourth set of color hues within the second image into a fourth color hue cluster;

means for determining that a third hue center of the third color hue cluster is within a distance range of a fourth hue center of the fourth color hue cluster;

means for generating (i) a third recolored image by recoloring the pixels of the first image having color hues outside the third color hue cluster and (ii) a fourth recolored image by recoloring the pixels of the second image having color hues outside the fourth color hue cluster; and

means for outputting an additional recolored collage comprising the third recolored image and the fourth recolored image, wherein the additional recolored collage comprises a smaller portion of remaining original color hues of the first image and the second image than the recolored collage.

15. The computing system of claim 9 , wherein the distance range comprises a 20 degree interval on a hue, saturation, lightness (HSL) color wheel.

16. A non-transitory computer-readable medium having instructions stored thereon, the instructions executable by a processing device to perform operations comprising:

receiving a first image from a set of collage images and a second image from the set of collage images;

grouping (i) a first set of color hues within the first image into a first color hue cluster and (ii) a second set of color hues within the second image into a second color hue cluster;

determining that a first hue center of the first color hue cluster is within a distance range of a second hue center of the second color hue cluster;

generating (i) a first recolored image by recoloring pixels of the first image having color hues outside the first color hue cluster and (ii) a second recolored image by recoloring pixels of the second image having color hues outside the second color hue cluster; and

outputting a recolored collage comprising the first recolored image and the second recolored image.

17. The non-transitory computer-readable medium of claim 16 , the instructions further executable by the processing device to perform operations comprising:

converting the set of collage images to a hue, saturation, lightness (HSL) color space; and

flattening the set of collage images in the HSL color space to remove saturation and lightness components, wherein the distance range comprises a 20 degree interval in the HSL color space.

18. The non-transitory computer-readable medium of claim 16 , wherein the first color hue cluster, the second color hue cluster, the first hue center, and the second hue center are computed using a k-means clustering operation, and wherein the k-means clustering operation comprises clustering the pixels of the first image into three different color hue clusters representing three ranges of color hues.

19. The non-transitory computer-readable medium of claim 16 , the instructions further executable by the processing device to perform operations comprising:

determining a collage layout grammar from a set of collage layout grammars that displays a largest portion of remaining original color hues located in the first recolored image and the second recolored image; and

placing the first recolored image and the second recolored image in the collage layout grammar.

20. The non-transitory computer-readable medium of claim 16 , the instructions further executable by the processing device to perform operations comprising:

grouping (i) a third set of color hues within the first image into a third color hue cluster and (ii) a fourth set of color hues within the second image into a fourth color hue cluster;

determining that a third hue center of the third color hue cluster is within a distance range of a fourth hue center of the fourth color hue cluster;

generating (i) a third recolored image by recoloring the pixels of the first image having color hues outside the third color hue cluster and (ii) a fourth recolored image by recoloring the pixels of the second image having color hues outside the fourth color hue cluster; and

outputting an additional recolored collage comprising the third recolored image and the fourth recolored image, wherein the additional recolored collage comprises a smaller portion of remaining original color hues of the first image and the second image than the recolored collage.

Assignments (2)
CHANGE OF NAME Recorded Mar 6, 2019
From: ADOBE SYSTEMS INCORPORATED
To: ADOBE INC.
Reel/Frame 048525/0042 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 6, 2018
From: RATHORE, SHAILENDRA SINGH; JAIN, ANANT; DHAWAN, ANMOL
To: ADOBE SYSTEMS INCORPORATED
Reel/Frame 046006/0816 →
Continuity (1)
Related Publication 20190378249A1 · Dec 12, 2019