IP Library › Granted Patent US 10,803,496
Granted Patent B1
US 10,803,496 · App. 16/189,643 · Granted Oct 13, 2020

Systems and methods for implementing machine vision and optical recognition

Inventor: John Hopkins (San Antonio, TX)
Assignee: United Services Automobile Association (USAA)
G06Q30/0278G06K9/64G06Q40/08G06T11/60
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 10,803,496
App. No.
16/189,643
Filed
Nov 13, 2018
Granted
Oct 13, 2020
Kind
B1
Art Unit
2665
USPC
382/103
Abstract

Embodiments disclosed herein may include a system including a server configured to receive from the mobile device the digital image capturing the object, execute an object recognition protocol to identify one or more image features of the digital image, determine an identification of the object based upon the one or more features of the digital image identified by the executed object recognition protocol, generate an object profile of the object based upon one or more data records of the object stored in the system databases where each respective record containing at least one data point corresponding to a valuation of the respective object, determine a value of the data point based upon the valuation of the respective object and a characteristic of a member, and transmit to the mobile device the object profile for the object captured in the digital image.

Claims (44)

1. A method comprising:

receiving, by a server, from an electronic device operated by a user, a digital image of an object;

determining by the server in a database, a user record comprising an object profile of the object containing a previously stored value of the object;

executing, by the server, a machine learning algorithm to determine one or more features of the object in the digital image, wherein the machine learning algorithm is trained based on a training dataset containing a collection of objects;

determining, by the server, location data of a place where the digital image was captured;

generating, by the server, one or more new data records of the object, each respective new data record containing at least one new data point corresponding to a valuation of the object;

generating, by the server, a new object profile of the object based upon the one or more new data records of the object;

determining, by the server, an updated value of the object based on the new object profile and the location data; and

transmitting, by the server to the electronic device, the updated value of the object, and the new object profile.

2. The method according to claim 1 , further comprising displaying, by the server on the electronic device, the updated value of the object, and the new object profile.

3. The method according to claim 1 , further comprising executing, by the server, image processing algorithms on the digital image to perform color and geometric corrections on the digital image.

4. The method according to claim 1 , wherein the electronic device is a mobile device of the user.

5. The method according to claim 1 , wherein the machine learning algorithm executes a classification function to label patches in the digital image to determine the one or more features of the object.

6. The method according to claim 1 , wherein the object profile further comprises previously captured image of the object.

7. The method according to claim 6 , further comprising determining, by the server, breakage on the object by comparing the digital image against the previously captured image of the object.

8. A system comprising:

a server configured to:

receive from an electronic device a digital image of an object;

identify a user record comprising an object profile of the object containing a previously stored value of the object;

execute a machine learning algorithm to determine one or more features of the object in the digital image, wherein the machine learning algorithm is trained based on a training dataset containing a collection of objects;

determine location data of a place where the digital image was captured;

generate one or more new data records of the object, each respective new data record containing at least one new data point corresponding to a valuation of the object;

generate a new object profile of the object based upon the one or more new data records of the object;

determine an updated value of the object based on the new object profile and the location data; and

transmit to the electronic device, the updated value of the object and the new object profile.

9. The system according to claim 8 , wherein the server is further configured to display, on the electronic device, the updated value of the object and the new object profile.

10. The system according to claim 8 , wherein the server is further configured to execute image processing algorithms on the digital image to perform color and geometric corrections on the digital image.

11. The system according to claim 8 , wherein the object profile further comprises previously captured image of the object.

12. The system according to claim 11 , wherein the server is further configured to determine breakage on the object by comparing the digital image against the previously captured image of the object.

13. A computer-implemented method comprising:

receiving, by a server, from a mobile device operated by a user, a digital image record containing a digital image capturing a first object;

determining, by the server, an object location of the first object based on geographical location coordinates associated with the digital image captured by the mobile device and contained within the digital image record;

executing by the server, an object recognition protocol to identify one or more image features of the digital image;

determining, by the server, an identification of the first object based upon the one or more image features of the digital image identified by the object recognition protocol;

identifying, by the server, a second object within a proximal distance of the object location by comparing the first object against a database comprising an object index of records containing information representing a plurality of objects based on their value in different locations, wherein the object index includes a record of the second object;

determining, by the server, a score between the first object and the second object by summing differences between corresponding cells of the first object and the second object;

determining, by the server, that the score satisfies a threshold for a number of cells matching the corresponding cells of the first object and the second object;

determining, by the server, a value of the first object based on a value of the second object and the score satisfying the threshold; and

transmitting, by the server to the mobile device, the value of the first object.

14. The method according to claim 13 , further comprising displaying, by the server on the mobile device the value of the object.

15. The method according to claim 13 , further comprising executing, by the server, image processing algorithms on the digital image to perform color and geometric corrections on the digital image.

16. The method according to claim 13 , further comprising:

determining, by the server, whether there are colored image regions within the digital image; and

upon determining presence of the colored image regions within the digital image, executing, by the server, a color detection process to identify the one or more image features of the digital image, the color detection process utilizing a look up table containing multiple colors stored in a memory.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 13, 2018
From: HOPKINS, JOHN
To: UNITED SERVICES AUTOMOBILE ASSOCIATION (USAA)
Reel/Frame 047489/0964 →
Continuity (1)
Continuation 15132108 · Apr 18, 2016
Cited By (35)
US 12,197,610 US 12,213,090 US 12,228,944 US 12,253,617 US 12,256,021 US 12,260,616 US 12,269,498 US 12,289,181 US 12,306,010 US 12,327,445 US 12,328,639 US 12,344,168 US 12,346,712 US 12,367,718 US 12,426,007 US 12,445,285 US 12,450,329 US 12,479,446 US 12,501,178 US 12,511,947 US 12,534,097 US 12,561,624 US 12,565,143 US 12,626,200 US 12,630,050 US 12,646,402 US 12,651,529 US 12,662,152 US 12,665,989 US 12,671,464 US 12,675,419 US 12,701,004 US 12,730,425 US 12,742,846 US 12,748,942