Dram c adjustment of automatic license plate recognition processing based on vehicle class information

• US 9,082,038 B2
• Filed: 05/29/2013
• Issued: 07/14/2015
• Est. Priority Date: 05/29/2013
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Kozitsky, Vladimir, Burry, Aaron Michael
• Primary Examiner(s): Abdi, Amara
• Application Number:
  US13/904,559
• Publication Number:
  US 20140355836A1
• Time in Patent Office: 776 Days
• Field of Search: 382/105
• US Class Current: 1/1
• CPC Class Codes: G06V 20/625 License plates
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/248 involving plural approaches, e.g. verification by template match; Resolving confusion among similar patterns, e.g. "O" versus "Q" G06V30/242 takes precedence

Abstract

Methods and systems for improving automated license plate recognition performance. One or more images of a vehicle can be captured via an automated license plate recognition engine. Vehicle class information associated with the vehicle can be obtained using the automated license place recognition engine. Such vehicle class information can be analyzed with respect to the vehicle. Finally, data can be dynamically adjusted with respect to the vehicle based on a per image basis to enhance recognition of the vehicle via the automated license plate recognition engine.

Claims

1. A method for improving automated license plate recognition performance, said method comprising:

capturing at least one image of at least one vehicle via an automated license plate recognition engine;

obtaining vehicle class information associated with said at least one vehicle;

analyzing said vehicle class information with respect to said at least one vehicle to thereby guide the automated license plate recognition engine; and

dynamically adjusting a key aspect of the automated license plate recognition engine based on the vehicle class information to thereby enhance recognition of said at least one vehicle via said automated license plate recognition engine.

2. The method of claim 1 wherein dynamically adjusting said data with respect to said at least one vehicle based on a per image basis, further comprises:

cropping at least one image associated with said at least one vehicle based on increasing granularity of said cropping to increase a processing speed of said automated license plate recognition engine.

3. The method of claim 1 wherein dynamically adjusting said data with respect to said at least one vehicle based on a per image basis, further comprises:

dynamically resizing said at least one image to improve a rate of capture of said at least one image and license plate data identified in said at least image.

4. The method of claim 1 wherein dynamically adjusting said data with respect to said at least one vehicle based on a per image basis, further comprises:

correcting OCR results with respect to said at least one image based on allowable character sequences for said vehicle class information with respect to said at least one vehicle.

5. The method of claim 1 wherein dynamically adjusting said data with respect to said at least one vehicle based on a per image basis, further comprises:

improving character level segmentation based on known license plate layouts based on said vehicle class information with respect to said at least one vehicle.

6. The method of claim 1 wherein obtaining vehicle class information associated with said at least one vehicle, further comprises:

obtaining said vehicle class information associated with said at least one vehicle from a source external to said automated license plate recognition engine; and

providing said vehicle class information to said automated license plate recognition engine.

7. The method of claim 6 wherein dynamically adjusting said data with respect to said at least one vehicle based on a per image basis, further comprises:

cropping at least one image associated with said at least one vehicle based on increasing granularity of said cropping to increase a processing speed of said automated license plate recognition engine;

dynamically resizing said at least one image to improve a rate of capture of said at least one image and license plate data identified in said at least image;

correcting OCR results with respect to said at least one image based on allowable character sequences for said vehicle class information with respect to said at least one vehicle; and

/or improving character level segmentation based on known license plate layouts based on said vehicle class information with respect to said at least one vehicle.

8. A system for improving automated license plate recognition performance, 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;

capturing at least one image of at least one vehicle via an automated license plate recognition engine;

obtaining vehicle class information associated with said at least one vehicle;

analyzing said vehicle class information with respect to said at least one vehicle to thereby guide the automated license plate recognition engine; and

dynamically adjusting a key aspect of the automated license plate recognition engine based on the vehicle class information to thereby enhance recognition of said at least one vehicle via said automated license plate recognition engine.

9. The system of claim 8 wherein said instructions are further configured for cropping at least one image associated with said at least one vehicle based on increasing granularity of said cropping to increase a processing speed of said automated license plate recognition engine.

10. The system of claim 8 wherein said instructions are further configured for dynamically resizing said at least one image to improve a rate of capture of said at least one image and license plate data identified in said at least image.

11. The system of claim 8 wherein said instructions are further configured for correcting OCR results with respect to said at least one image based on allowable character sequences for said vehicle class information with respect to said at least one vehicle.

12. The system of claim 8 wherein said instructions are further configured for improving character level segmentation based on known license plate layouts based on said vehicle class information with respect to said at least one vehicle.

13. The system of claim 8 wherein said instructions are further configured for:

obtaining said vehicle class information associated with said at least one vehicle from a source external to said automated license plate recognition engine; and

providing said vehicle class information to said automated license plate recognition engine.

14. The system of claim 13 wherein said instructions are further configured for:

cropping at least one image associated with said at least one vehicle based on increasing granularity of said cropping to increase a processing speed of said automated license plate recognition engine;

dynamically resizing said at least one image to improve a rate of capture of said at least one image and license plate data identified in said at least image;

correcting OCR results with respect to said at least one image based on allowable character sequences for said vehicle class information with respect to said at least one vehicle; and

/or improving character level segmentation based on known license plate layouts based on said vehicle class information with respect to said at least one vehicle.

15. A non-transitory processor-readable medium storing computer code representing instructions to cause a process for improving automated license plate recognition performance, said computer code further comprising code to:

capture at least one image of at least one vehicle via an automated license plate recognition engine;

obtain vehicle class information associated with said at least one vehicle;

analyze said vehicle class information with respect to said at least one vehicle to thereby guide the automated license plate recognition engine; and

dynamically adjust a key aspect of the automated license plate recognition engine based on the vehicle class information to thereby enhance recognition of said at least one vehicle via said automated license plate recognition engine.

16. The processor-readable medium of claim 15 wherein said code further comprises code to crop at least one image associated with said at least one vehicle based on increasing granularity of said cropping to increase a processing speed of said automated license plate recognition engine.

17. The processor-readable medium of claim 15 wherein said code further comprises code to dynamically resize said at least one image to improve a rate of capture of said at least one image and license plate data identified in said at least image.

18. The processor-readable medium of claim 15 wherein said code further comprises code to correct OCR results with respect to said at least one image based on allowable character sequences for said vehicle class information with respect to said at least one vehicle.

19. The processor-readable medium of claim 15 wherein said code further comprises code to improve character level segmentation based on known license plate layouts based on said vehicle class information with respect to said at least one vehicle.

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

obtain said vehicle class information associated with said at least one vehicle from a source external to said automated license plate recognition engine; and

provide said vehicle class information to said automated license plate recognition engine.