IP Library Granted Patent US 12,602,937
Granted Patent B2
US 12,602,937 · App. 18/251,561 · Granted Apr 14, 2026

Systems, methods, and interfaces for identifying coating surfaces

Inventors: Francis J. Groves (McMurray, PA); Kathleen M. Chrobak (Fombell, PA); William R. Wright (Pittsburgh, PA)
Assignee: THE PITTSBURGH PAINTS COMPANY
G06V20/64G06T7/90G06T11/10
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 12,602,937
App. No.
18/251,561
Filed
May 3, 2023
Granted
Apr 14, 2026
Kind
B2
Art Unit
2681
USPC
382/181
Abstract

A computer system for dynamically parsing a digital image to identify coating surfaces can receive a user-provided input comprising an indication of a particular environment, and a user-provided digital image of an environment. The computer system can also identify, with an image recognition module, one or more objects within the user-provided digital image. Additionally, the computer system can create a modified digital image by parsing the identified objects from the user-provided digital image and identify surfaces within the modified digital image. The computer system can also identify a proposed color for the surfaces within the modified digital image and generate a colorized digital image by integrating the proposed color on at least one surface and integrating the parsed one or more objects in the modified digital image.

Claims (77)

1 . A computer system for dynamically parsing a digital image to identify coating surfaces, comprising:

one or more processors; and

one or more computer-readable media having stored thereon executable instructions that when executed by the one or more processors configure the computer system to perform at least the following:

receive, through a network connection, a user-provided input comprising an indication of a particular environment;

receive, through the network connection, a user-provided digital image, wherein the digital image comprises a picture of an environment and one or more objects;

identify, with an image recognition module, the one or more objects within the user-provided digital image;

create a modified digital image by parsing the identified one or more objects from the user-provided digital image;

identify surfaces within the modified digital image;

identifying at least one proposed color for the surfaces within the modified digital image, wherein identifying at least one proposed color for the surfaces within the modified digital image comprises:

obtaining data about an age of a user,

accessing a color-age look-up table, wherein the color-age look-up table comprises color prevalence in association with various ages,

accessing a digital architectural template look-up table, wherein the digital architectural template look-up table comprises color prevalence in association with a database subset of one or more digital architectural templates based on the data about the age of the user,

identifying correlations between the color-age look-up table and the digital architectural template look-up table, and

generating at least one proposed color based on the identified correlations between the color-age look-up table and the digital architectural template look-up table; and

generate a colorized digital image by integrating the at least one proposed color on at least one surface and integrating the parsed one or more objects in the modified digital image.

2 . The computer system of claim 1 , wherein identifying, with the image recognition module, one or more objects within the user-provided digital image comprises:

accessing, within a digital architectural template database, a database subset of one or more digital architectural templates for the particular environment; and

mapping one or more digital architectural templates from the database subset to the one or more objects within the user-provided digital image.

3 . The computer system of claim 2 , wherein the image recognition module comprises a machine learning algorithm.

4 . The computer system of claim 1 , wherein identifying at least one proposed color for the surfaces within the modified digital image comprises:

identifying at least one color of at least one of the parsed one or more objects; and

generating at least one proposed color based on the at least one identified color of at least one of the parsed one or more objects.

5 . The computer system of claim 1 , wherein identifying at least one proposed color for the surfaces within the modified digital image comprises:

identifying at least one color of at least one of the parsed one or more objects;

organizing the parsed one or more objects by a permanence attribute with respect to the particular environment; and

generating at least one proposed color based on the at least one identified colors and permanence attributes associated with the parsed one or more objects.

6 . The computer system of claim 1 , wherein identifying at least one proposed color for the surfaces within the modified digital image comprises:

obtaining geographic data about a user;

accessing a color-geographic look-up table, wherein the color-geographic look-up table comprises color prevalence in association with various geographic regions; and

generating at least one proposed color based on the geographic data about the user.

7 . A computerized method for use on a computer system comprising one or more processors and one or more computer-readable media having stored thereon executable instructions that when executed by the one or more processors configure the computer system to perform a method of dynamically parsing a digital image to identify coating surfaces, the method comprising:

receiving, through a network connection, a user-provided input comprising an indication of a particular environment;

receiving, through the network connection, a user-provided digital image, wherein the digital image comprises a picture of an environment and one or more objects;

identifying, with an image recognition module, the one or more objects within the user-provided digital image;

creating a modified digital image by parsing the identified one or more objects from the user-provided digital image;

identifying surfaces within the modified digital image;

identifying at least one proposed color for the surfaces within the modified digital image, wherein identifying at least one proposed color for the surfaces within the modified digital image comprises:

obtaining geographic data about a user,

accessing a color-geographic look-up table, wherein the color-geographic look-up table comprises color prevalence in association with various geographic regions,

accessing a digital architectural template look-up table, wherein the digital architectural template look-up table comprises color prevalence in association with a database subset of one or more digital architectural templates based on the geographic data about the user,

identifying correlations between the color-geographic look-up table and the digital architectural template look-up table, and

generating at least one proposed color based on the identified correlations between the color-geographic look-up table and the digital architectural template look-up table; and

generating a colorized digital image by integrating the at least one proposed color on at least one surface and integrating the parsed one or more objects in the modified digital image.

8 . The computerized method of claim 7 , wherein identifying, with the image recognition module, one or more objects within the user-provided digital image comprises:

accessing, within a digital architectural template database, a database subset of one or more digital architectural templates for the particular environment; and

mapping one or more digital architectural templates from the database subset to the one or more objects within the user-provided digital image.

9 . The computerized method of claim 8 , wherein the image recognition module comprises a machine learning algorithm.

10 . The computerized method of claim 7 , wherein identifying at least one proposed color for the surfaces within the modified digital image comprises:

identifying at least one color of at least one of the parsed one or more objects; and

generating at least one proposed color based on the at least one identified color of at least one of the parsed one or more objects.

11 . The computerized method of claim 7 , wherein identifying at least one proposed color for the surfaces within the modified image comprises:

identifying at least one color of at least one of the parsed one or more objects;

organizing the parsed one or more objects by a permanence attribute with respect to the particular environment; and

generating at least one proposed color based on the identified colors and permanence attributes associated with the parsed one or more objects.

12 . The computerized method of claim 8 , wherein accessing, within a digital architectural template database, a database subset of one or more digital architectural templates for the particular environment comprises:

obtaining data about an age of a user;

accessing an age look-up table, wherein the age look-up table comprises one or more digital architectural templates in association with various ages; and

generating the database subset of one or more digital architectural templates based on the data about the age of the user.

13 . The computerized method of claim 7 , wherein identifying at least one proposed color for the surfaces within the modified digital image comprises:

obtaining data about an age of a user;

accessing a color-age look-up table, wherein the color-age look-up table comprises color prevalence in association with various ages;

accessing a digital architectural template look-up table, wherein the digital architectural template look-up table comprises color prevalence in association with a database subset of one or more digital architectural templates based on the data about the age of the user;

identifying correlations between the color-age look-up table and the digital architectural template look-up table; and

generating at least one proposed color based on the identified correlations between the color-age look-up table and the digital architectural template look-up table.

14 . A computer program product comprising one or more non-transitory computer storage media having stored thereon computer-executable instructions that, when executed at a processor, cause a computer system to perform a method for dynamically parsing a digital image to identify coating surfaces, the method comprising:

receiving, through a network connection, a user-provided input comprising an indication of a particular environment;

receiving, through the network connection, a user-provided digital image, wherein the digital image comprises a picture of an environment and one or more objects;

identifying, with an image recognition module, the one or more objects within the user-provided digital image;

creating a modified digital image by parsing the identified one or more objects from the user-provided digital image;

identifying surfaces within the modified digital image;

identifying at least one proposed color for the surfaces within the modified digital image, wherein identifying at least one proposed color for the surfaces within the modified digital image comprises:

obtaining geographic data about a user,

accessing a color-geographic look-up table, wherein the color-geographic look-up table comprises color prevalence in association with various geographic regions,

accessing a digital architectural template look-up table, wherein the digital architectural template look-up table comprises color prevalence in association with a database subset of one or more digital architectural templates based on the geographic data about the user,

identifying correlations between the color-geographic look-up table and the digital architectural template look-up table, and

generating at least one proposed color based on the identified correlations between the color-geographic look-up table and the digital architectural template look-up table; and

generating a colorized digital image by integrating the at least one proposed color on at least one surface and integrating the parsed one or more objects in the modified digital image.

Assignments (5)
CORRECTIVE ASSIGNMENT TO CORRECT THE THE OMITTED PAGE OF PATENT SCHEDULE PREVIOUSLY RECORDED AT REEL: 70139 FRAME: 552. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Mar 13, 2025
From: PPG INDUSTRIES OHIO, INC.
To: A-PAINT BIDCO, INC.
Reel/Frame 070511/0557 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 7, 2025
From: PPG INDUSTRIES OHIO, INC.
To: A-PAINT BIDCO, INC.
Reel/Frame 070139/0552 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 7, 2025
From: A-PAINT BIDCO, INC.
To: THE PITTSBURGH PAINTS CO.
Reel/Frame 070146/0875 →
SECURITY AGREEMENT Recorded Dec 26, 2024
From: PPG ARCHITECTURAL FINISHES, INC.
To: ALLY BANK, AS COLLATERAL AGENT
Reel/Frame 069784/0592 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 3, 2023
From: GROVES, FRANCIS J.; CHROBAK, KATHLEEN M.; WRIGHT, WILLIAM R.
To: PPG INDUSTRIES OHIO, INC.
Reel/Frame 063517/0808 →
Continuity (2)
Provisional Application 63110821 · Nov 6, 2020
Related Publication 20240013557A1 · Jan 11, 2024
References Cited (79)
US 3653771A · Piringer · 1972 [cited by applicant]
US 5556694A · Austin · 1996 [cited by applicant]
US 5579031A · Liang · 1996 [cited by applicant]
US 5726800A · Ezra et al. · 1998 [cited by applicant]
US 5883708A · Jung et al. · 1999 [cited by applicant]
US 6252564B1 · Albert et al. · 2001 [cited by applicant]
US 6825829B1 · Albert et al. · 2004 [cited by applicant]
US 9538041B1 · Chapman · 2017 [cited by applicant]
US 9832868B1 · Wright et al. · 2017 [cited by applicant]
US 20020008751A1 · Spurgeon et al. · 2002 [cited by applicant]
US 20020012895A1 · Lehmann · 2002 [cited by applicant]
US 20020018281A1 · Theiste et al. · 2002 [cited by applicant]
US 20020089513A1 · Blanchard et al. · 2002 [cited by applicant]
US 20020190975A1 · Kerr · 2002 [cited by applicant]
US 20030011560A1 · Albert et al. · 2003 [cited by applicant]
US 20030151611A1 · Turpin et al. · 2003 [cited by applicant]
US 20050007483A1 · Zimmermann et al. · 2005 [cited by applicant]
US 20050099630A1 · Reynolds et al. · 2005 [cited by applicant]
US 20050270299A1 · Rasmussen et al. · 2005 [cited by applicant]
US 20050280823A1 · Lewis et al. · 2005 [cited by applicant]
US 20060152527A1 · Minchew et al. · 2006 [cited by applicant]
US 20070146325A1 · Poston et al. · 2007 [cited by applicant]
US 20080107856A1 · Argoitia et al. · 2008 [cited by applicant]
US 20090201309A1 · Demos · 2009 [cited by examiner]
US 20100310916A1 · Coish et al. · 2010 [cited by applicant]
US 20110006110A1 · Cleary et al. · 2011 [cited by applicant]
US 20110018895A1 · Buzyn et al. · 2011 [cited by applicant]
US 20110018896A1 · Buzyn et al. · 2011 [cited by applicant]
US 20110070453A1 · Mai et al. · 2011 [cited by applicant]
US 20110148218A1 · Rozbicki · 2011 [cited by applicant]
US 20120122066A1 · Dohring et al. · 2012 [cited by applicant]
US 20120170836A1 · Henry et al. · 2012 [cited by applicant]
US 20130004678A1 · Krasnov et al. · 2013 [cited by applicant]
US 20130121608A1 · Winnemoeller et al. · 2013 [cited by applicant]
US 20140157210A1 · Katz et al. · 2014 [cited by applicant]
US 20140191771A1 · Nam et al. · 2014 [cited by applicant]
US 20140231625A1 · Chang et al. · 2014 [cited by applicant]
US 20140304265A1 · Topakas et al. · 2014 [cited by applicant]
US 20140360663A1 · Lee et al. · 2014 [cited by applicant]
US 20150009420A1 · Zhou · 2015 [cited by applicant]
US 20150116346A1 · Somerville et al. · 2015 [cited by applicant]
US 20150212785A1 · Chiba et al. · 2015 [cited by applicant]
US 20150331970A1 · Jovanovic · 2015 [cited by applicant]
US 20160033792A1 · Blum et al. · 2016 [cited by applicant]
US 20160275702A1 · Reynolds et al. · 2016 [cited by applicant]
US 20170074652A1 · Send et al. · 2017 [cited by applicant]
US 20170124370A1 · He et al. · 2017 [cited by applicant]
US 20170150001A1 · Chapman · 2017 [cited by applicant]
US 20170161822A1 · Crogan et al. · 2017 [cited by applicant]
US 20170242570A1 · Beymore et al. · 2017 [cited by applicant]
US 20180081481A1 · Fournier et al. · 2018 [cited by applicant]
US 20180125605A1 · Kim-Whitty · 2018 [cited by applicant]
US 20180300023A1 · Hein · 2018 [cited by applicant]
US 20180321425A1 · Hart et al. · 2018 [cited by applicant]
US 20190034020A1 · He et al. · 2019 [cited by applicant]
US 20190080341A1 · Eilenberger et al. · 2019 [cited by applicant]
US 20190114727A1 · Spath · 2019 [cited by applicant]
US 20190138168A1 · Mckers et al. · 2019 [cited by applicant]
US 20190149808A1 · Ng et al. · 2019 [cited by applicant]
US 20190272712A1 · Taya · 2019 [cited by applicant]
US 20190287303A1 · Falstrup et al. · 2019 [cited by applicant]
US 20200035024A1 · Price et al. · 2020 [cited by applicant]
US 20210406974A1 · Minchew et al. · 2021 [cited by applicant]
US 20220237832A1 · Williams · 2022 [cited by examiner]
CN 205929678U · 2017 [cited by applicant]
CN 109575874A · 2019 [cited by applicant]
DE 0441032C · 1927 [cited by applicant]
DE 102011014853A1 · 2012 [cited by applicant]
EP 0484564A1 · 1992 [cited by applicant]
GB 2434227A · 2007 [cited by applicant]
JP 53061054U · 1978 [cited by applicant]
WO 9839915A1 · 1998 [cited by applicant]
WO 9910767A1 · 1999 [cited by applicant]
WO 2007053710A2 · 2007 [cited by applicant]
WO 2013082009A1 · 2013 [cited by applicant]
WO 2017188470A1 · 2017 [cited by applicant]
International Search Report and Written Opinion received for PCT Application Serial No. PCT/US2021/054580 dated Feb. 9, 2022, 10 pages. [cited by applicant]
Office Action received for Australian Patent Application No. 2021376041, mailed on Sep. 4, 2023, 4 pages. [cited by applicant]
Office Action received for Australian Patent Application No. 2021376041, mailed on Mar. 13, 2024, 4 pages. [cited by applicant]