IP Library Granted Patent US 9,247,106
Granted Patent B2
US 9,247,106 · App. 14/665,350 · Granted Jan 26, 2016

Color correction based on multiple images

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 9,247,106
App. No.
14/665,350
Granted
Jan 26, 2016
Kind
B2
Abstract

In some implementations, a method provides color corrections based on multiple images. In some implementations, a method includes determining one or more characteristics of each of a plurality of source images and determining one or more similarities between the one or more characteristics of different source images. The source images are grouped into one or more groups of one or more target images based on the determined similarities. The method determines and applies one or more color corrections to the one or more target images in at least one of the groups.

Claims (55)

1. A computer-implemented method to correct image color, the method comprising:

obtaining a plurality of images having one or more similarities in one or more characteristics of the plurality of images;

determining, using a hardware processor, one or more color corrections for the plurality of images;

estimating one or more confidence levels associated with the one or more color corrections; and

applying the one or more color corrections to the plurality of images with a magnitude based on the associated one or more confidence levels.

2. The method of claim 1 wherein the one or more confidence levels are based on at least one of:

the one or more characteristics of the plurality of images; and

the one or more similarities in the one or more characteristics of the plurality of images.

3. The method of claim 1 wherein the one or more confidence levels are based at least in part on the number of images in the plurality of images.

4. The method of claim 1 wherein the one or more confidence levels are based on a plurality of factors used to determine the one or more color corrections, wherein one or more of the plurality of factors are weighted more than one or more other factors of the plurality of factors in the estimation of the one or more confidence levels.

5. The method of claim 4 wherein the plurality of factors used to determine the one or more color corrections include at least one of:

one or more hue distributions in the plurality of images; and

one or more reference colors obtained from one or more reference images associated with one or more of the plurality of images.

6. The method of claim 1 wherein estimating the one or more confidence levels includes estimating the one or more confidence levels based on a plurality of factors used to determine the one or more color corrections, including assigning each factor an individual confidence level and summing the individual confidence levels of the factors to obtain an overall confidence level for the one or more color corrections.

7. The method of claim 1 wherein the one or more confidence levels are based at least in part on timestamps of the plurality of images being within a predetermined time range of each other.

8. The method of claim 1 wherein the one or more characteristics include color data derived from hues of pixels of the source images, wherein the one or more color corrections adjust one or more hues of the pixels in the one or more target images.

9. The method of claim 1 wherein the one or more characteristics includes at least one of: a time of capture of each image, a setting of a camera capturing each image, a distribution of color data in each image, and at least one object depicted in each image.

10. The method of claim 1 wherein the color correction is based on a hue distribution averaged over the plurality of images, and wherein the estimated confidence level is based at least in part on the number of images over which the hue distribution is averaged.

11. The method of claim 1 further comprising:

determining one or more characteristics of each of multiple source images, wherein the plurality of images are included in the multiple source images;

determining the one or more similarities between the one or more characteristics of the plurality of images; and

grouping the plurality of images into a group, wherein the group is different than one or more other groups of other images of the multiple source images.

12. The method of claim 1 further comprising:

determining that at least one of the one or more color corrections does not affect at least one of the plurality of images;

determining one or more different color corrections for the at least one of the plurality of images; and

repeating the estimating and applying using the one or more different color corrections for the at least one of the plurality of images.

13. The method of claim 12 wherein determining that at least one of the one or more color corrections does not affect at least one of the plurality of images is based on at least one of:

the one or more confidence levels associated with the at least one of the one or more color corrections; and

input from a user rejecting the at least one of the one or more color corrections.

14. The method of claim 1 wherein the one or more color corrections correct at least one color property of the plurality of images, the at least one color property including at least one of: color balance, brightness, contrast, and sharpness.

15. A system to correct image color, the system comprising:

a storage device; and

at least one processor operative to access the storage device and configured to:

obtain a plurality of images having one or more similarities in one or more characteristics of the plurality of images;

determine one or more color corrections for the plurality of images;

estimate one or more confidence levels associated with the one or more color corrections;

determine which of the one or more color corrections are qualified to be applied based on the associated one or more confidence levels; and

apply the one or more qualifying color corrections to the plurality of images with a magnitude based on the associated one or more confidence levels.

16. The system of claim 15 wherein the one or more confidence levels are based on at least one of:

the one or more characteristics of the plurality of images;

the one or more similarities in the one or more characteristics of the plurality of images;

a plurality of factors used to determine the associated one or more color corrections; and

the number of images in the plurality of images.

17. The system of claim 15 wherein the one or more confidence levels are based on a plurality of factors used to determine the one or more color corrections, wherein one or more of the plurality of factors are weighted more than one or more other factors of the plurality of factors in the estimation of the one or more confidence levels.

18. A computer readable storage medium having stored thereon instructions to correct image color that, when implemented by a processor, cause the processor to:

obtain a plurality of images having one or more similarities in one or more characteristics of the plurality of images;

determine, using a hardware processor, one or more color corrections for the plurality of images;

estimate one or more confidence levels associated with the one or more color corrections; and

apply the one or more color corrections to the plurality of images with a magnitude based on the associated one or more confidence levels.

19. The computer readable medium of claim 18 wherein the one or more confidence levels are based on at least one of:

the one or more characteristics of the plurality of images;

the one or more similarities in the one or more characteristics of the plurality of images;

a plurality of factors used to determine the associated one or more color corrections; and

the number of images in the plurality of images.

20. The computer readable medium of claim 18 wherein the instructions causing the processor to estimate the one or more confidence levels includes instructions causing the processor to estimate the one or more confidence levels based on a plurality of factors used to determine the one or more color corrections, including assigning each factor an individual confidence level and summing the individual confidence levels of the factors to obtain an overall confidence level for the one or more color corrections.

Assignments (2)
CHANGE OF NAME Recorded Oct 2, 2017
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 044566/0657 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 23, 2015
From: KRISHNASWAMY, ARAVIND; BUTKO, NICHOLAS; COHEN, DAVID
To: GOOGLE INC.
Reel/Frame 035233/0643 →