IP Library › Granted Patent US 12,333,503
Granted Patent B2
US 12,333,503 · App. 18/327,308 · Granted Jun 17, 2025

Visualization of damage on images

Inventors: Micah Price (Anna, TX); Geoffrey Dagley (McKinney, TX); Avid Ghamsari (Frisco, TX); Qiaochu Tang (The Colony, TX); Staevan Duckworth (The Colony, TX)
Assignee: Capital One Services, LLC
G06Q10/20G06N3/08G06T7/001G06T7/12G06T7/74G06V10/235G06V10/25G06V10/764G06V20/20G06T2200/24
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 12,333,503
App. No.
18/327,308
Granted
Jun 17, 2025
Kind
B2
Abstract

A device may receive images of an object and information identifying the object, process the images using an artificial intelligence technique to identify parts of the object that are depicted in the images, and receive information identifying a location of damage on the object and information regarding the damage on the object. The device may process the information identifying the location of damage to identify a damaged part of the object, identify images depicting the damaged part, and identify, in the images, a location of the damaged part. The device may generate a first content item for display at the location of the damaged part in the images and generate a second content item for display with the images based on user interaction with the first content item, where the second content item includes information based on the information regarding the damage on the object.

Claims (112)

1. A method, comprising:

obtaining, by a device, a plurality of images of a vehicle and information identifying one or more parts of the vehicle,

wherein the plurality of images:

were obtained from a variety of types of cameras, and

had a variety of lighting conditions;

processing, by the device using an artificial intelligence technique, the plurality of images to form a standardized plurality of images,

wherein the standardized plurality of images have a common lighting condition;

processing, by the device, the standardized plurality of images to identify the one or more parts of the vehicle;

receiving, by the device, information identifying a location of damage on the vehicle and information regarding the damage on the vehicle;

processing, by the device, the information identifying the location of the damage on the vehicle to identify a damaged part of the vehicle;

identifying, by the device and from the plurality of images, one or more images depicting the damaged part of the vehicle;

storing, by the device, information identifying the damaged part of the vehicle and the information identifying one or more parts of the vehicle; and

transmitting, by the device and to a server device, a content item with the one or more images depicting the damaged part of the vehicle,

wherein the content item includes an image of the damaged part displayed at a location, in the one or more images, that is adjacent to the location of the damage on the vehicle; and

wherein the content item includes a geometric shape based on a type of the damage on the vehicle.

2. The method of claim 1 , wherein transmitting the content item comprises:

transmitting a first type of content item for a first type of damage in the image of the damaged part and transmitting a second type of content item for a second type of damage in the image of the damaged part.

3. The method of claim 1 , further comprising:

obtaining another plurality of images of the vehicle;

identifying, in the other plurality of images, parts of the vehicle using the artificial intelligence technique; and

identifying, in one or more of the other plurality of images, the damaged part of the vehicle.

4. The method of claim 1 , further comprising:

storing the information identifying the damaged part of the vehicle and information identifying the vehicle in a data structure.

5. The method of claim 1 , further comprising:

receiving information identifying the vehicle,

wherein the information identifying the vehicle includes one or more of:

a make of the vehicle,

a model of the vehicle,

a year of the vehicle, or

a vehicle identification number (VIN).

6. The method of claim 1 , further comprising:

receiving, from another device, a user selection of a filtering option; and

transmitting, to the other device, the one or more images depicting the damaged part of the vehicle without transmitting one or more other images, of the plurality of images, that do not depict the damaged part of the vehicle.

7. The method of claim 1 , further comprising:

generating the content item for display with the one or more images depicting the damaged part of the vehicle,

wherein the content item includes information regarding the damage on the vehicle.

8. A device, comprising:

one or more memories; and

one or more processors, communicatively coupled to the one or more memories, configured to:

obtain a plurality of images of a vehicle and information identifying one or more parts of the vehicle,

wherein the plurality of images:

were obtained from a variety of types of cameras, and

had a variety of lighting conditions;

process, using an artificial intelligence technique, the plurality of images to form a standardized plurality of images,

wherein the standardized plurality of images have a common brightness condition;

process the standardized plurality of images to identify the one or more parts of the vehicle;

receive information identifying a location of damage on the vehicle and information regarding the damage on the vehicle;

process the information identifying the location of the damage on the vehicle to identify a damaged part of the vehicle;

identify, from the plurality of images, one or more images depicting the damaged part of the vehicle;

store information identifying the damaged part of the vehicle and the information identifying one or more parts of the vehicle; and

transmit, to a server device, a content item with the one or more images depicting the damaged part of the vehicle,

wherein the content item includes a geometric shape for display at a location, in the one or more images depicting the damaged part of the vehicle, that is adjacent to the location of the damage on the vehicle,

wherein the geometric shape is based on a type of the damage on the vehicle.

9. The device of claim 8 , wherein the one or more processors are further configured to:

provide, to another device, characteristics of the vehicle including one or more of:

vehicle mileage,

vehicle price, or

vehicle color.

10. The device of claim 8 , wherein the one or more processors are further configured to:

receive another plurality of images of the vehicle;

identify, in the other plurality of images, parts of the vehicle using the artificial intelligence technique; and

identify, in one or more of the other plurality of images, the damaged part of the vehicle.

11. The device of claim 8 , wherein the one or more processors are further configured to:

transmit a first type of content item for a first type of damage in the one or more images of the damaged part and transmit a second type of content item for a second type of damage in the one or more images of the damaged part.

12. The device of claim 8 , wherein the one or more processors are further configured to:

receive information identifying the vehicle,

wherein the information identifying the vehicle includes one or more of:

a make of the vehicle,

a model of the vehicle,

a year of the vehicle, or

a vehicle identification number (VIN).

13. The device of claim 8 , wherein the one or more processors are further configured to:

receive, from another device, a user selection of a filtering option; and

transmit, to the other device, the one or more images depicting the damaged part of the vehicle without transmitting one or more other images, of the plurality of images, that do not depict the damaged part of the vehicle.

14. The device of claim 8 , wherein the geometric shape includes one or more of:

a circle,

a triangle, or

a square.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors to:

obtain a plurality of images of a vehicle and information identifying one or more parts of the vehicle,

wherein the plurality of images:

were obtained from a variety of types of cameras, and

had a variety of lighting conditions;

process, using an artificial intelligence technique, the plurality of images to form a standardized plurality of images,

wherein the standardized plurality of images have a common aspect ratio;

process the standardized plurality of images to identify the one or more parts of the vehicle;

receive information identifying a location of damage on the vehicle and information regarding the damage on the vehicle;

process the information identifying the location of the damage on the vehicle to identify a damaged part of the vehicle;

identify, from the plurality of images, one or more images depicting the damaged part of the vehicle; and

transmit, to a server device, a content item with the one or more images depicting the damaged part of the vehicle,

wherein the content item includes an overlay for display at a location, in the one or more images depicting the damaged part of the vehicle, that is adjacent to the location of the damage on the vehicle,

wherein the overlay is a geometric shape based on a type of the damage of the vehicle.

16. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

receive another plurality of images of the vehicle;

identify, in the other plurality of images, parts of the vehicle using the artificial intelligence technique; and

identify, in one or more of the other plurality of images, the damaged part of the vehicle.

17. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

store the information identifying one or more parts of the vehicle and information identifying the vehicle in a data structure.

18. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

receive information identifying the vehicle,

wherein the information identifying the vehicle includes one or more of:

a make of the vehicle,

a model of the vehicle,

a year of the vehicle, or

a vehicle identification number (VIN).

19. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

receive, from another device, a user selection of a filtering option; and

transmit, to the other device, the one or more images depicting the damaged part of the vehicle without transmitting one or more other images, of the plurality of images, that do not depict the damaged part of the vehicle.

20. The non-transitory computer-readable medium of claim 15 , wherein the overlay includes one or more of:

a colored overlay, or

a patterned overlay.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 2, 2023
From: PRICE, MICAH; DAGLEY, GEOFFREY; GHAMSARI, AVID; TANG, QIAOCHU; DUCKWORTH, STAEVAN
To: CAPITAL ONE SERVICES, LLC
Reel/Frame 063835/0799 →
Continuity (3)
Continuation 17301423 · Apr 2, 2021
Continuation 16741320 · Jan 13, 2020
Related Publication 20230306381A1 · Sep 28, 2023
References Cited (52)
US 8094182B2 · Park et al. · 2012 [cited by applicant]
US 8879813B1 · Solanki · 2014 [cited by examiner]
US 9218626B1 · Haller, Jr. et al. · 2015 [cited by applicant]
US 9412203B1 · Garcia, III et al. · 2016 [cited by applicant]
US 10031906B2 · Campbell et al. · 2018 [cited by applicant]
US 10332209B1 · Brandmaier et al. · 2019 [cited by applicant]
US 10360601B1 · Adegan · 2019 [cited by applicant]
US 10475160B1 · Conroy et al. · 2019 [cited by applicant]
US 10610098B1 · Soliz · 2020 [cited by examiner]
US 10699168B1 · Xu · 2020 [cited by applicant]
US 10891694B1 · Leise et al. · 2021 [cited by applicant]
US 10970835B1 · Price et al. · 2021 [cited by applicant]
US 11080838B1 · Li · 2021 [cited by examiner]
US 11430069B1 · Pedersen · 2022 [cited by examiner]
US 11556995B1 · Little · 2023 [cited by examiner]
US 20020115423A1 · Hatae et al. · 2002 [cited by applicant]
US 20040148188A1 · Uegaki · 2004 [cited by examiner]
US 20050251427A1 · Dorai et al. · 2005 [cited by applicant]
US 20090055043A1 · Mian et al. · 2009 [cited by applicant]
US 20100241946A1 · Ofek · 2010 [cited by examiner]
US 20110180107A1 · Dahl · 2011 [cited by examiner]
US 20160093078A1 · Davis · 2016 [cited by examiner]
US 20170061459A1 · Dow et al. · 2017 [cited by applicant]
US 20170061506A1 · Dow et al. · 2017 [cited by applicant]
US 20170098014A1 · Rawlings · 2017 [cited by examiner]
US 20170147991A1 · Franke et al. · 2017 [cited by applicant]
US 20180121888A1 · O'Reilly · 2018 [cited by examiner]
US 20180260793A1 · Li et al. · 2018 [cited by applicant]
US 20180350163A1 · Pofale et al. · 2018 [cited by applicant]
US 20190026558A1 · Tanigawa · 2019 [cited by examiner]
US 20190095877A1 · Li · 2019 [cited by examiner]
US 20190185186A1 · Li · 2019 [cited by examiner]
US 20190286153A1 · Rankawat · 2019 [cited by examiner]
US 20200035195A1 · Maeng · 2020 [cited by examiner]
US 20200074222A1 · Guo et al. · 2020 [cited by applicant]
US 20200111061A1 · Stucki et al. · 2020 [cited by applicant]
US 20200118365A1 · Wang et al. · 2020 [cited by applicant]
US 20200143519A1 · Gordon · 2020 [cited by examiner]
US 20200231109A1 · Baltaxe · 2020 [cited by examiner]
US 20200351543A1 · Kerofsky et al. · 2020 [cited by applicant]
US 20200394813A1 · Theverapperuma · 2020 [cited by examiner]
US 20210118141A1 · Huang · 2021 [cited by examiner]
US 20210192264A1 · Li et al. · 2021 [cited by applicant]
US 20210224968A1 · Price et al. · 2021 [cited by applicant]
US 20210310955A1 · Dahan · 2021 [cited by examiner]
US 20220036463A1 · Faga · 2022 [cited by examiner]
US 20220148050A1 · Gandhi et al. · 2022 [cited by applicant]
US 20230012796A1 · Liu et al. · 2023 [cited by applicant]
US 20230143738A1 · Kim · 2023 [cited by examiner]
Wang, Xinkuang, Wenjing Li, and Zhongcheng Wu. “Cardd: A new dataset for vision-based car damage detection.” IEEE Transactions on Intelligent Transportation Systems 24.7 (2023): 7202-7214. (Year: 2023). [cited by examiner]
Spencer Jr, Billie F., Vedhus Hoskere, and Yasutaka Narazaki. “Advances in computer vision-based civil infrastructure inspection and monitoring.” Engineering 5.2 (2019): 199-222. (Year: 2019). [cited by examiner]
Chen Q, Gan X, Huang W, Feng J, Shim H. Road damage detection and classification using mask R-CNN with DenseNet backbone. Comput. Mater. Contin. Jan. 1, 2020;65(3):2201-15. (Year: 2020). [cited by examiner]