Systems and methods for using image analysis to automatically determine vehicle information

• US 10,255,516 B1
• Filed: 08/18/2017
• Issued: 04/09/2019
• Est. Priority Date: 08/29/2016
• Status: Active Grant

• Current Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Original Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Inventors: Antonetti, Joseph, Imran, Abid, Loew, Justin, Moon, Calvin, Foreman, Gary
• Primary Examiner(s): Yang, Qian
• Application Number:
  US15/680,837
• Time in Patent Office: 599 Days
• CPC Class Codes: G06F 18/217 Validation; Performance evaluation; Active pattern learning techniques
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1916 Validation; Performance evaluation
• CPC Class Codes: G06V 30/1918 Fusion techniques, i.e. combining data from various sources, e.g. sensor fusion
• CPC Class Codes: G06V 30/1983 Syntactic or structural pattern recognition, e.g. symbolic string recognition
• CPC Class Codes: G06V 30/262 using context analysis, e.g. lexical, syntactic or semantic context

Abstract

The present disclosure is directed to systems and methods for analyzing digital images to determine alphanumeric strings depicted in the digital images. An electronic device may generate a set of filtered images using a received digital image. The electronic device may also perform an optical character recognition (OCR) technique on the set of filtered images, and may filter out any of the set of filtered images according to a set of rules. The electronic device may further identify a set of common elements representative of the alphanumeric string depicted in the digital image, and determine a machine-encoded alphanumeric string based on the set of common elements.

Claims

1. A computer-implemented method of analyzing image data associated with a vehicle of an individual, the method comprising:

accessing a digital image depicting an alphanumeric string;

generating, by a computer processor, a set of filtered digital images using the digital image;

analyzing, by the computer processor, the set of filtered digital images using an optical character recognition (OCR) technique, the analyzing resulting in a set of OCR results respectively associated with the set of filtered digital images;

analyzing the set of OCR results to identify a set of common elements representative of the alphanumeric string depicted in the digital image; and

determining a machine-encoded alphanumeric string based on the set of common elements.

2. The computer-implemented method of claim 1, further comprising:

applying a set of rules to the set of OCR results to remove at least a portion of the set of OCR results.

3. The computer-implemented method of claim 2, wherein applying the set of rules to the set of OCR results comprises:

determining, for an OCR result of the set of OCR results, that the OCR result indicates a string comprising a number of digits that exceeds a threshold number of digits; and

removing the OCR result.

4. The computer-implemented method of claim 2, wherein applying the set of rules to the set of OCR results comprises:

accessing a previously-reported metric associated with an account of the individual;

comparing the previously-reported metric to an OCR result of the set of OCR results to determine that content of the OCR result is not possible; and

removing the OCR result.

5. The computer-implemented method of claim 1, wherein analyzing the set of OCR results to identify the set of common elements comprises:

analyzing the set of OCR results using at least one string metric to identify the set of common elements.

6. The computer-implemented method of claim 1, wherein generating the set of filtered digital images using the digital image comprises:

generating a first filtered digital image by applying a first digital filter to the digital image; and

generating a second filtered digital image by applying a second digital filter to the digital image.

7. The computer-implemented method of claim 1, wherein analyzing the set of filtered digital images using the optical character recognition (OCR) technique comprises:

analyzing the set of filtered digital images using the OCR technique to determine a preliminary machine-encoded alphanumeric string depicted in each of the set of filtered digital images.

8. The computer-implemented method of claim 7, further comprising:

calculating a confidence level of each character included in the preliminary machine-encoded alphanumeric string.

9. The computer-implemented method of claim 1, wherein each of the set of OCR results includes a confidence level for each character in the respective OCR result, and wherein determining the machine-encoded alphanumeric string based on the set of common elements comprises:

determining each character of the machine-encoded alphanumeric string based on the confidence level for each character in the respective OCR result.

10. The computer-implemented method of claim 1, further comprising:

calculating a confidence level of each character included in the machine-encoded alphanumeric string; and

storing, in memory, the machine-encoded alphanumeric string and the confidence level of each character included in the machine-encoded alphanumeric string.

11. A system for analyzing image data associated with a vehicle of an individual, comprising:

a memory storing a set of computer-executable instructions; and

a processor interfacing with the memory, and configured to execute the computer-executable instructions to cause the processor to;

access a digital image depicting an alphanumeric string,

generate a set of filtered digital images using the digital image,

analyze the set of filtered digital images using an optical character recognition (OCR) technique, the analyzing resulting in a set of OCR results respectively associated with the set of filtered digital images,

analyze the set of OCR results to identify a set of common elements representative of the alphanumeric string depicted in the digital image, and

determine a machine-encoded alphanumeric string based on the set of common elements.

12. The system of claim 11, wherein the processor is configured to execute the computer-executable instructions to further cause the processor to:

apply a set of rules to the set of OCR results to remove at least a portion of the set of OCR results.

13. The system of claim 12, wherein to apply the set of rules to the set of OCR results, the processor is configured to:

determine, for an OCR result of the set of OCR results, that the OCR result indicates a string comprising a number of digits that exceeds a threshold number of digits, and

remove the OCR result.

14. The system of claim 12, wherein to apply the set of rules to the set of OCR results, the processor is configured to:

access a previously-reported metric associated with an account of the individual,

compare the previously-reported metric to an OCR result of the set of OCR results to determine that content of the OCR result is not possible, and

remove the OCR result.

15. The system of claim 11, wherein to analyze the set of OCR results to identify the set of common elements, the processor is configured to:

analyzing the set of OCR results using at least one string metric to identify the set of common elements.

16. The system of claim 11, wherein to generate the set of filtered digital images using the digital image, the processor is configured to:

generate a first filtered digital image by applying a first digital filter to the digital image, and

generate a second filtered digital image by applying a second digital filter to the digital image.

17. The system of claim 11, wherein to analyze the set of filtered digital images using the optical character recognition (OCR) technique, the processor is configured to:

analyze the set of filtered digital images using the OCR technique to determine a preliminary machine-encoded alphanumeric string depicted in each of the set of filtered digital images.

18. The system of claim 17, wherein the processor is configured to execute the computer-executable instructions to further cause the processor to:

calculate a confidence level of each character included in the preliminary machine-encoded alphanumeric string.

19. The system of claim 11, wherein each of the set of OCR results includes a confidence level for each character in the respective OCR result, and wherein to determine the machine-encoded alphanumeric string based on the set of common elements, the processor is configured to:

determine each character of the machine-encoded alphanumeric string based on the confidence level for each character in the respective OCR result.

20. The system of claim 11, wherein the processor is configured to execute the computer-executable instructions to further cause the processor to:

calculate a confidence level of each character included in the machine-encoded alphanumeric string, and

store, in the memory, the machine-encoded alphanumeric string and the confidence level of each character included in the machine-encoded alphanumeric string.