Methods and systems for increasing the automation of license plate reading accuracy

1. A method for increasing automation of license plate reading accuracy, comprising:

searching by a correlation search process, ALPR (Automatic License Plate Recognition) results against an ALPR database of previous ALPR results and data contained in a correlation database comprising truthed values, in response to an ALPR read by an ALPR search engine with respect to a license plate;

providing the ALPR results of the correlation search process to a correlation decision engine;

constructing at least one confidence level associated with a processed frame, wherein the at least one confidence level is constructed with the correlation decision engine for a correlation to a known previous license plate read based on a number of parameters and a number of times that the parameters match, in response to a match found in the ALPR database for a parameter contained in the ALPR database as a result of the correlation search process; and

tuning the at least one confidence level to increase an accuracy of subsequent automatic ALPR results by the ALPR search engine as a part of a correlation and feedback system; and

increasing the at least one confidence level comprising a correlation confidence of the correlation search process, in response to determining when a transaction has been disputed based on the parameters match.

2. The method of claim 1 wherein the correlation decision engine determines when the match is found.

3. The method of claim 2 further comprising:

outputting decision data from the correlation decision engine for automation with the at least one confidence level comprising a high confidence match to a known license plate.

4. The method of claim 2 further comprising:

outputting decision data from the correlation decision engine for inclusion with a manual image review of an image containing the license plate.

5. The method of claim 1 further comprising:

tuning the at least one confidence level to increase an accuracy of subsequent automatic ALPR results by the ALPR search engine; and

providing search results of the correlation search process to a correlation decision engine the determines when the match is found.

6. The method of claim 5 further comprising:

outputting decision data from the correlation decision engine for automation with the at least one confidence level comprising a high confidence match to a known license plate; and

outputting decision data from the correlation decision engine for inclusion with a manual image review of an image containing the license plate.

7. A system for increasing automation of license plate reading accuracy, the system comprising:

a hardware processor;

an automatic license plate recognition (ALPR) database comprising previous ALPR results;

an input interface for facilitating searching by a correlation search process, ALPR results against the ALPR database comprising previous ALPR results and data contained in a correlation database comprising truthed values, when an ALPR read by an ALPR search engine occurs with respect to a license plate; and

wherein the ALPR results of the correlation search process are provided to a correlation decision engine,

wherein at least one confidence level is associated with a processed frame and is constructed with the correlation decision engine for a correlation to a known previous license plate read based on a number of parameters and a number of times that the parameters match, when a match is found in the ALPR database with respect to the parameters contained in the ALPR database as a result of the correlation search process;

wherein the at least one confidence level is tunable to increase an accuracy of subsequent automatic ALPR results by the ALPR search engine as a part of a correlation and feedback system; and

wherein the at least one confidence level comprising a correlation confidence of the correlation search process is increased, in response to determining when a transaction has been disputed based on the parameters match.

8. The system of claim 7 wherein the correlation decision engine determines when the match is found.

9. The system of claim 8 wherein:

decision data is output from the correlation decision engine for automation with the at least one confidence level comprising a high confidence match to a known license plate.

10. The system of claim 8 wherein:

decision data is output from the correlation decision engine for inclusion with a manual image review of an image containing the license plate.

11. The system of claim 7 wherein:

The at least one confidence level is tunable to increase an accuracy of subsequent automatic ALPR results by the ALPR search engine; and

search results of the correlation search process are provided to a correlation decision engine the determines when the match is found.

12. The system of claim 7 wherein:

decision data from the correlation decision engine is output for automation with the at least one confidence level comprising a high confidence match to a known license plate; and

decision data from the correlation decision engine is output for inclusion with a manual image review of an image containing the license plate.

13. A non-transitory computer program product for increasing automation of license plate reading accuracy, the non-transitory computer program product comprising:

one or more computer readable storage media and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:

program instructions to

search by a correlation search process, ALPR (Automatic License Plate Recognition) results against an ALPR database of previous ALPR results and data contained in a correlation database comprising truthed values, in response to an ALPR read by an ALPR search engine occurs with respect to a license plate;

provide the ALPR results of the correlation search process to a correlation decision engine;

construct at least one confidence level associated with a processed frame, wherein the at least one confidence level is constructed with the correlation decision engine for a correlation to a known previous license plate read based on a number of parameters and a number of times that the parameters match, in response to a match found in the ALPR database for a parameter contained in the ALPR database as a result of the correlation search process; and

tune the at least one confidence level to increase an accuracy of subsequent automatic ALPR results by the ALPR search engine as a part of a correlation and feedback system; and

increase the at least one confidence level comprising a correlation confidence of the correlation search process, in response to determining when a transaction has been disputed based on the parameters match.

14. The non-transitory computer program product of claim 13 , wherein the correlation decision engine determines when the match is found.

15. The non-transitory computer program product of claim 14 , further comprising: program instructions, collectively stored on the one or more computer readable storage media, to output decision data from the correlation decision engine for automation with the at least one confidence level comprising a high confidence match to a known license plate.

16. The non-transitory computer program product of claim 14 , further comprising: program instructions, collectively stored on the one or more computer readable storage media, to output decision data from the correlation decision engine for inclusion with a manual image review of an image containing the license plate.

17. The non-transitory computer program product of claim 14 , further comprising: program instructions, collectively stored on the one or more computer readable storage media, to:

tune the at least one confidence level to increase an accuracy of subsequent automatic ALPR results by the ALPR search engine; and

provide search results of the correlation search process to a correlation decision engine the determines when the match is found.