IP Library Granted Patent US 12,254,532
Granted Patent B1
US 12,254,532 · App. 18/092,304 · Granted Mar 18, 2025

Automated color correction of studio images to provide a consistent standard of appearance

Inventors: Pratik Mohan Ramdasi (Sunnyvale, CA); Hasan Cheema (San Francisco, CA); Agustin Mautone (Montevideo, UY); Fabrizio Albertoni (Montevideo, UY); Maria Paz Cuturi (Montevideo, UY)
Assignee: The RealReal, Inc.
G06T11/001G06T2210/22
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 12,254,532
App. No.
18/092,304
Granted
Mar 18, 2025
Kind
B1
Abstract

A color correction system comprises a correction information generator and an image processor. The correction information generator generates color correction information from a color correction image associated with a plurality of images. The image processor automatically processes the plurality of images based on the color correction information to generate a plurality of color-corrected images. In operation, images and a color correction image associated with the images are received. Next, color correction information is generated from the color correction image. For example, color correction information includes a color correction matrix or white balance parameters. Next, the images are automatically processed based on the color correction information thereby generating color-corrected images. The system automates color correction processing of studio images to provide highly scalable and reliable color correction. Significant quantities of studio images are consistently color-corrected based on processing of the color correction image.

Claims (28)

1. A system comprising:

a correction information generator that generates color correction information from a color correction image associated with a plurality of images, wherein the correction information generator processes an image of a color checker card in the color correction image to generate the color correction information, and wherein the correction information generator processes the image of the color checker card by performing operations of:

generating a thumbnail image of the color correction image;

detecting the image of the color checker card in the thumbnail Image of the color correction image; and

detecting color checker patch segments in the detected image of the color checker card, wherein the correction information generator generates a color correction matrix [A] from the color checker patch segments, and wherein the color correction matrix [A] represents the color correction information; and

an image processor that automatically processes the plurality of images based on the color correction information to generate a plurality of color-corrected images.

2. The system of claim 1 , wherein the correction information generator generates the color correction matrix [A] by solving a matrix equation [P]=[O]*[A], wherein O are identified colors from the color checker patch segments, and wherein P are referenced colors of the color checker card.

3. A system comprising:

a correction information generator that generates color correction information from a color correction image associated with a plurality of images, wherein the correction information generator processes an image of a color checker card in the color correction image to generate the color correction information, and wherein the correction information generator processes the image of the color checker card by performing operations of:

generating a thumbnail image of the color correction image;

detecting the image of the color checker card in the thumbnail image of the color correction image; and

detecting color checker patch segments in the detected image of the color checker card, wherein the correction information generator generates a color correction matrix [A] from the color checker patch segments, and wherein the color correction matrix [A] represents the color correction information; and

an image processor that automatically processes the plurality of images based on the color correction information to generate a plurality of color-corrected images, wherein the image processor automatically processes each image in the plurality of images by performing operations of:

generating a thumbnail image of each image in the plurality of images;

cropping the thumbnail image of each image in the plurality of images to generate a cropped image; and

processing the cropped image with the color correction matrix [A] to generate a color-corrected version of the cropped image.

4. A system comprising:

a correction information generator that generates color correction information from a color correction image associated with a plurality of images, wherein the correction information generator processes an image of a color checker card in the color correction image to generate the color correction information, and wherein the correction information generator processes the image of the color checker card by performing operations of:

generating a thumbnail image of the color correction image;

detecting the image of the color checker card in the thumbnail image of the color correction image; and

detecting color checker patch segments in the detected image of the color checker card;

an image processor that automatically processes the plurality of Images based on the color correction information to generate a plurality of color-corrected images;

a white balance processor that performs a white balance operation on a selected color checker patch segment to generate white balance parameters; and

an optimization minimizer that processes the color checker patch segments to generate one or more additional parameters comprising at least one of exposure, gamma, and brightness parameters, wherein the white balance parameters and the one or more additional parameters form correction parameters that represent the color correction information.

5. The system of claim 4 , wherein the selected color checker patch segment is segment number 22 .

6. The system of claim 4 , wherein the image processor automatically processes each image in the plurality of images by performing operations of:

applying the correction parameters to each image in the plurality of images to generate the plurality of color-corrected images; and

cropping the color-corrected images to generate final color-corrected images.

Assignments (5)
SECURITY INTEREST Recorded Feb 29, 2024
From: THE REALREAL, INC.
To: GLAS TRUST COMPANY LLC, AS NOTES COLLATERAL AGENT
Reel/Frame 066605/0991 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 12, 2023
From: RAMDASI, PRATIK MOHAN; CHEEMA, HASAN
To: THE REALREAL, INC.
Reel/Frame 062358/0476 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 12, 2023
From: MAUTONE, AGUSTIN
To: TRYOLABS S.A.
Reel/Frame 062358/0780 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 12, 2023
From: ALBERTONI, FABRIZIO; CUTURI, MARIA PAZ
To: TRYOLABS S.A.
Reel/Frame 062358/0916 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 12, 2023
From: TRYOLABS S.A.
To: THE REALREAL, INC.
Reel/Frame 062359/0040 →
References Cited (12)
US 8294781B2 · Cote et al. · 2012 [cited by applicant]
US 9712743B2 · Corcoran et al. · 2017 [cited by applicant]
US 9911242B2 · Sundaresan et al. · 2018 [cited by applicant]
US 10027938B2 · Fujiwara et al. · 2018 [cited by applicant]
US 10783615B2 · Ma et al. · 2020 [cited by applicant]
US 20080088858A1 · Marcu et al. · 2008 [cited by applicant]
US 20090059256A1 · Hasegawa · 2009 [cited by examiner]
US 20180176528A1 · Li et al. · 2018 [cited by applicant]
US 20220245900A1 · Tan · 2022 [cited by examiner]
CN 109040598B · 2020 [cited by applicant]
JP 4681529B2 · 2011 [cited by applicant]
JP 2020155907A · 2020 [cited by applicant]