Method and system for automatically determining the issuing state of a license plate

• US 9,082,037 B2
• Filed: 05/22/2013
• Issued: 07/14/2015
• Est. Priority Date: 05/22/2013
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Burry, Aaron Michael, Kozitsky, Vladimir
• Primary Examiner(s): FUJITA, KATRINA R
• Application Number:
  US13/899,742
• Publication Number:
  US 20140348392A1
• Time in Patent Office: 783 Days
• US Class Current: 1/1
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• CPC Class Codes: G06V 20/625 License plates

Abstract

Methods and systems for automatically determining the issuing state of a license plate. An image of a license plate acquired by an ALPR engine can be processed via one or more OCR engines such that each OCR engine among the OCR engines is tuned to a particular state. Confidence data output from the OCR engine(s) can be analyzed (among other factors) to estimate the issuing state associated with the license plate. Multiple observations related to the issuing state can be merged to derive an overall conclusion and assign an associated confidence value with respect to the confidence data and determine a likely issuing state associated with the license plate.

Claims

1. A method for automatically determining the issuing state of a license plate, said method comprising:

processing via at least one optical character recognition engine, an image of a license plate acquired by an automatic license plate recognition engine, wherein each optical character recognition engine among said at least one optical character recognition engine is tuned to a particular state;

analyzing confidence data output from said at least one optical character recognition engine to estimate an issuing state associated with said license plate, said estimated issuing state and said confidence output comprising a font based observation from said at least one optical character recognition engine;

analyzing a syntax associated with said image of said license plate to estimate an issuing state associated with said license plate, said estimated issuing state comprising a syntax based observation; and

merging multiple observations comprising said font based observation and said syntax based observation related to said issuing state to derive an overall conclusion and assign an associated confidence value with respect to said confidence data and determine a likely issuing state associated with said license plate.

2. The method of claim 1 further comprising merging said multiple observations using a Bayesian-based approach.

3. The method of claim 1 further comprising estimating said likely issuing state based on intermediate confidence data output from said at least one optical character recognition engine.

4. The method of claim 1 further comprising estimating said likely issuing state based on character sequence data derived from said image of said license plate and output from said at least one optical character recognition engine.

5. The method of claim 1 further comprising calculating at least one joint distribution between actual states and estimated states associated with said license plate to further estimate said issuing state.

6. The method of claim 1 further comprising calculating at least one joint distribution between estimates of said issuing state to further estimate said issuing state.

7. The method of claim 1 further comprising analyzing ground truth labels to obtain prior probability data associated with likely issuing states associated with said license plate and assist in estimating said issuing state.

8. A system for automatically determining the issuing state of a license plate, said system comprising:

a processor;

a data bus coupled to said processor; and

a computer-usable medium embodying computer program code, said computer-usable medium being coupled to said data bus, said computer program code comprising instructions executable by said processor and configured for;

processing via at least one optical character recognition engine, an image of a license plate acquired by an automatic license plate recognition engine, wherein each optical character recognition engine among said at least one optical character recognition engine is tuned to a particular state;

analyzing confidence data output from said at least one optical character recognition engine to estimate an issuing state associated with said license plate, said estimated issuing state and said confidence output comprising a font based observation from said at least one optical character recognition engine;

analyzing a syntax associated with said image of said license plate to estimate an issuing state associated with said license plate, said estimated issuing state comprising a syntax based observation; and

merging multiple observations comprising said font based observation and said syntax based observation related to said issuing state to derive an overall conclusion and assign an associated confidence value with respect to said confidence data and determine a likely issuing state associated with said license plate.

9. The system of claim 8 wherein said instructions are further configured for merging said multiple observations using a Bayesian-based approach.

10. The system of claim 8 wherein said instructions are further configured for estimating said likely issuing state based on intermediate confidence data output from said at least one optical character recognition engine.

11. The system of claim 8 wherein said instructions are further configured for estimating said likely issuing state based on character sequence data derived from said image of said license plate and output from said at least one optical character recognition engine.

12. The system of claim 8 wherein said instructions are further configured for calculating at least one joint distribution between actual states and estimated states associated with said license plate to further estimate said issuing state.

13. The system of claim 8 wherein said instructions are further configured for calculating at least one joint distribution between estimates of said issuing state to further estimate said issuing state.

14. The system of claim 8 wherein said instructions are further configured for analyzing ground truth labels to obtain prior probability data associated with likely issuing states associated with said license plate and assist in estimating said issuing state.

15. A non-transitory processor-readable medium storing computer code representing instructions to cause a process for automatically determining the issuing state of a license plate, said computer code further comprising code to:

process via at least one optical character recognition engine, an image of a license plate acquired by an automatic license plate recognition engine, wherein each optical character recognition engine among said at least one optical character recognition engine is tuned to a particular state;

analyze confidence data output from said at least one optical character recognition engine to estimate an issuing state associated with said license plate, said estimated issuing state and said confidence output comprising a font based observation from said at least one optical character recognition engine;

analyze a syntax associated with said image of said license plate to estimate an issuing state associated with said license plate, said estimated issuing state comprising a syntax based observation; and

merge multiple observations comprising said font based observation and said syntax based observation related to said issuing state to derive an overall conclusion and assign an associated confidence value with respect to said confidence data and determine a likely issuing state associated with said license plate.

16. The non-transitory processor-readable medium of claim 15 wherein said code further comprises code to merge said multiple observations using a Bayesian-based approach.

17. The non-transitory processor-readable medium of claim 15 wherein said code further comprises code to estimate said likely issuing state based on intermediate confidence data output from said at least one optical character recognition engine.

18. The non-transitory processor-readable medium of claim 15 wherein said code further comprises code to estimate said likely issuing state based on character sequence data derived from said image of said license plate and output from said at least one optical character recognition engine.

19. The non-transitory processor-readable medium of claim 15 wherein said code further comprises code to calculate at least one joint distribution between actual states and estimated states associated with said license plate to further estimate said issuing state.

20. The non-transitory processor-readable medium of claim 15 wherein said code further comprises code to:

calculate at least one joint distribution between estimates of said issuing state to further estimate said issuing state; and

analyze ground truth labels to obtain prior probability data associated with likely issuing states associated with said license plate and assist in estimating said issuing state.