Verifying odometer mileage using captured images and optical character recognition (OCR)

Patent metadata

Field	Value
Publication number	US-11250283-B1
Application number	US-201916705619-A
Country	US
Kind code	B1
Filing date	Dec 6, 2019
Priority date	Apr 16, 2015
Publication date	Feb 15, 2022
Grant date	Feb 15, 2022

Abstract

An odometer verification method includes capturing an odometer image at a threshold date, calculating a first and a second mileage using OCR, determining whether the first and the second mileage match, and updating a user profile associated with the insurance policy. A non-transitory, tangible computer-readable medium stores machine readable instructions in a mobile computing device, that when executed by a processor, cause the processor to capture an odometer image at a threshold date, calculate a first and a second mileage using OCR, determine whether the first and the second mileage match, and update a user profile. A mobile computing device includes an image capture unit configured to capture an odometer image at a threshold date, perform a first and a second OCR, determine whether the first and the second mileage match, and update the insurance policy user profile of the vehicle.

First claim

What is claimed:

1. A computer-implemented method for verifying an odometer mileage corresponding to a vehicle, the method comprising:
capturing, via a mobile computing device, an image of an odometer corresponding to the vehicle in response to passage of a threshold date prior to expiration of an insurance policy associated with the vehicle;
performing, via the mobile computing device, a first and a second optical character recognition (OCR) process on the image of the odometer to calculate a first and a second odometer mileage, respectively;
determining, via the mobile computing device, whether the first and the second odometer mileage match to verify the odometer mileage; and
updating, via the mobile computing device, a user profile associated with the insurance policy to indicate the odometer mileage.

2. The computer-implemented method of claim 1 , wherein the act of performing the first OCR process comprises:
performing a matrix matching OCR process.

3. The computer-implemented method of claim 1 , wherein the act of performing the second OCR process further comprises:
performing a feature extraction or an adaptive recognition OCR process.

4. The computer-implemented method of claim 1 , wherein performing the first OCR process and the second OCR process on the image of the odometer to respectively calculate the first odometer mileage and the second odometer mileage includes one or both of (i) improving the accuracy of the first OCR process using a machine learning technique, and (ii) improving the accuracy of the second OCR process using a machine learning technique.

5. The computer-implemented method of claim 1 , further comprising:
adding, by one or more processors, metadata to the image of the odometer indicative of a communication status of the computing device when the image of the odometer was captured.

6. The computer-implemented method of claim 5 , further comprising:
generating, by one or more processors, a manual review flag when the metadata indicates that the computing device was not in communication with the vehicle when the image was captured.

7. The computer-implemented method of claim 1 , further comprising:
displaying, based upon the updated user profile, one or both of (i) an insurance premium, and (ii) an insurance discount.

8. A non-transitory, tangible computer-readable medium storing machine readable instructions in a mobile computing device, that when executed by a processor, cause the processor to:
capture an image of an odometer of a vehicle in response to passage of a threshold date prior to expiration of an insurance policy associated with the vehicle;
perform a first and a second optical character recognition (OCR) process on the image to calculate a first and a second odometer mileage, respectively;
determine whether the first and the second odometer mileage match to verify the vehicle odometer mileage, and
update a user profile associated with the insurance policy associated with the vehicle to indicate the vehicle odometer mileage.

9. The non-transitory, tangible computer-readable medium of claim 8 , wherein the first OCR process includes a matrix matching OCR process.

10. The non-transitory, tangible computer-readable medium of claim 8 , wherein the second OCR process includes a feature extraction or an adaptive recognition OCR process.

11. The non-transitory, tangible computer-readable medium of claim 8 , including further instructions that, when executed by a processor, cause the processor to:
one or both of (i) improve the accuracy of the first OCR process using a machine learning technique, and (ii) improve the accuracy of the second OCR process using a machine learning technique.

12. The non-transitory, tangible computer-readable medium of claim 8 , including further instructions that, when executed, cause the processor to:
add metadata to the image of the odometer indicative of a communication status of the mobile computing device when the image of the odometer was captured.

13. The non-transitory, tangible computer-readable medium of claim 12 , including further instructions that, when executed, cause the processor to generate a manual review flag in response to determining, based upon the metadata, that the mobile computing device was not communicating with the vehicle when the image was captured.

14. The non-transitory, tangible computer-readable medium of claim 8 , further including instructions, that when executed by the processor, cause the processor to:
display, based upon the updated user profile, one or both of (i) an insurance premium, and (ii) an insurance discount.

15. A mobile computing device, comprising:
one or more processors; and
one or more memories including computer-executable instructions that, when executed by the one or more processors, cause the mobile computing device to:
capture an image of an odometer of a vehicle in response to passage of a threshold date prior to expiration of an insurance policy associated with a user account profile corresponding to the vehicle,
perform a first and a second optical character recognition (OCR) process on the image to calculate a first and a second odometer mileage, respectively,
determine whether the first and the second odometer mileage match to verify the vehicle odometer mileage, and
update the user profile associated with the insurance policy associated with the vehicle to indicate the vehicle odometer mileage.

16. The mobile computing device of claim 15 , wherein the image capture unit is further configured to:
one or both of (i) improve the accuracy of the first OCR process using a machine learning technique, and (ii) improve the accuracy of the second OCR process using a machine learning technique.

17. The mobile computing device of claim 15 , wherein the image capture unit is further configured to perform a feature extraction or an adaptive recognition OCR process as the second OCR process.

18. The mobile computing device of claim 15 , wherein the image capture unit is further configured to generate a failed OCR validation indicator when the first and the second odometer mileage do not match.

19. The mobile computing device of claim 15 , further comprising:
a processor configured to add metadata to the image of the odometer indicative of a communication status of the mobile computing device when the image of the odometer was captured, and generate a manual review flag when the metadata indicates that the mobile computing device was not communicating with the vehicle when the image was captured.

20. The mobile computing device of claim 15 , wherein the image capture unit is further configured to:
display, based upon the updated user profile, one or both of (i) an insurance premium, and (ii) an insurance discount.

Assignees

• State Farm Mutual Automobile Insurance Co

Inventors

• Clauss Mark E
• Thurber David W
• Riley Sr Matthew Eric
• Lovings Richard J
• Balbach Steven Joseph
• Baker Nicholas R
• Wilson J Lynn

Classifications

• G06V30/10

  Character recognition · CPC title

• G06V30/224

  of printed characters having additional code marks or containing code marks · CPC title

• G06Q40/08 Primary

  Insurance · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06V20/63

  Scene text, e.g. street names · CPC title