METHODS AND SYSTEMS FOR ACCURATELY RECOGNIZING VEHICLE LICENSE PLATES

• US 20170300786A1
• Filed: 09/14/2016
• Published: 10/19/2017
• Est. Priority Date: 10/01/2015
• Status: Active Grant

• Current Assignee: IntelliVision Technologies Corp. (Melrose Industries Plc)
• Original Assignee: Intelli-Vision
• Inventors: Gope, Chandan, Gupta, Gagan, Jindal, Nitin, Agarwal, Amit
• Granted Patent: US 10,706,330 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06T 5/20 using local operators
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/625 License plates
• CPC Class Codes: G06V 30/19173 Classification techniques

Abstract

The present invention discloses methods, systems and computer programmable products for detecting license plates and recognizing characters in the licence plates. The system receives an image and identifies one or more regions including a license plate. The one or more regions are converted into a plurality of binarized images, which are then filtered to remove noise. Next, one or more clusters of characters are identified in the plurality of binarized images. The one or more clusters of characters are analyzed to recognize a set of characters, wherein each character in the set includes a confidence value.

Claims

1. A license plate detection and recognition (LPDR) system comprising of:

a processor, a non-transitory storage element coupled to the processor, encoded instructions stored in the non-transitory storage element, wherein the encoded instructions when implemented by the processor, configure the LPDR system to;

receive an image by an image input unit, wherein the image input unit receives the image from at least one of an image capturing device, a network, a computer and a memory unit;

detect one or more regions in the image by a license plate detection unit, wherein a region of the one or more regions includes a license plate, the license plate detection unit further comprising;

a binarization unit configured to generate a set of binarized images of the region using at least one of a multi-scale difference of Gaussian filter and a variable adaptive threshold (T), wherein the variable adaptive threshold (T) is computed based on at least one parameter of a set of parameters computed locally in a window centered at a location in the region; and

a filtration unit configured to remove noise from a binarized image of the set of binarized images based on at least one of a horizontal profile and a vertical profile of the binarized image;

detect one or more clusters of characters in the binarized image by a character detection unit based on at least one cluster constraint of the group comprising number of characters, size and orientation of characters, spacing between characters, aspect ratio and slope of characters; and

recognize a set of characters from the detected one or more clusters of characters by a character recognition unit, wherein a character of the set of characters is associated with a confidence value.

2. The LPDR system of claim 1, wherein the one or more regions detected by the license plate detection unit include license plates of different sizes.

3. The LPDR system of claim 1, wherein the license plate detection unit is further configured to create a list of thresholds based on the variable adaptive threshold (T), wherein the list of thresholds comprises N values in the range of {f*T, g*T}, where f<

1 and g>

1.

4. The LPDR system of claim 1, wherein the set of parameters comprises at least one of the group comprising a mean, a median, a mode and a standard deviation of pixel intensity in the window.

5. The LPDR system of claim 1 is further configured to detect one or more vehicles in the image.

6. The LPDR system of claim 1, wherein the license plate detection unit further comprises a license plate verification unit configured to detect the one or more regions in the image based on at least one of the group comprising color, edges, transition in edges, shape, size, orientation, Histogram of Gradients (HoGs) and a machine-learning based classifier.

7. The LPDR system of claim 1, wherein each of the horizontal profile and the vertical profile of the binarized image is generated based on one or more transition points identified by scanning the binarized image, wherein each of the one or more transition points represents one of a transition from black to white and a transition from white to black.

8. The LPDR system of claim 1, wherein the character recognition unit recognizes the set of characters using a classifier, and wherein the classifier is based on at least one of a supervised and an unsupervised machine-learning network.

9. The LPDR system of claim 1 further comprising a postprocessor, wherein the postprocessor is configured to validate the set of characters recognized by the character recognition unit.

10. The LPDR system of claim 9, wherein the post processor is further configured to validate the set of characters based on at least one of the group comprising spatial arrangement of characters, frequency of occurrence of characters and a set of pre-determined rules.

11. A computer programmable product for detecting a region containing a license plate and, detecting and recognizing a set of characters in the region, the computer programmable product being a part of a license plate detection and recognition (LPDR) system, the computer programmable product including a set of instructions, that are when executed by a processor of the LPDR system, causes the LPDR system to:

receive an image, wherein the image is received from at least one of an image capturing device, a network, a computer and a memory unit;

detect one or more regions in the image, wherein a region of the one or more regions includes a license plate, further comprising;

generate a set of binarized images of the region using at least one of a multi-scale difference of Gaussian filter and a variable adaptive threshold (T), wherein the variable adaptive threshold (T) is computed based on at least one parameter of a set of parameters computed locally in a window centered at a location in the region; and

remove noise from a binarized image of the set of binarized images based on at least one of a horizontal profile and a vertical profile of the binarized image;

detect one or more clusters of characters in the binarized image based on at least a cluster constraint of the group comprising number of characters, size and orientation of characters, spacing between characters and slope of characters; and

recognize a set of characters from the detected one or more clusters of characters, wherein a character of the set of characters is associated with a confidence value.

12. The computer programmable product of claim 11 causes the LPDR system to further create a list of thresholds based on the variable adaptive threshold (T), wherein the list of thresholds comprises N values in the range of {f*T, g*T}, where f<

1 and g>

1.

13. The computer programmable product of claim 11 causes the LPDR system to further detect one or more vehicles in the image.

14. The computer programmable product of claim 11, wherein the one or more regions in the image are detected based on at least one of the group comprising color, edges, transition in edges, shape, size, orientation, Histogram of Gradients (HoGs) and a machine-learning based classifier.

15. The computer programmable product of claim 11, wherein each of the horizontal profile and the vertical profile of the binarized image is generated based on one or more transition points identified by scanning the binarized image, wherein each of the one or more transition points represents one of a transition from black to white and a transition from white to black.

16. The computer programmable product of claim 11 causes the LPDR system to further validate the set of characters recognized by the character recognition unit.

17. A method for detecting and recognizing a license plate, the method comprising:

detecting one or more regions in an image, wherein a region of the one or more regions includes a license plate, comprising;

generating a set of binarized images of the region using at least one of a multi-scale difference of Gaussian filter and a variable adaptive threshold (T), wherein the variable adaptive threshold (T) is computed based on at least one parameter of a set of parameters computed locally in a window centered at a location in the region; and

removing noise from a binarized image of the set of binarized images based on at least one of a horizontal profile and a vertical profile of the binarized image;

detecting one or more clusters of characters in the binarized image based on at least one cluster constraint of the group comprising number of characters, size and orientation of characters, spacing between characters and slope of characters; and

recognizing a set of characters from the detected one or more clusters of characters, wherein a character of the set of characters is associated with a confidence value.

18. The method for detecting and recognizing a license plate of claim 17 further comprising receiving the image from at least one of an image capturing device, a network and a memory unit.

19. The method for detecting and recognizing a license plate of claim 17, wherein the image is a frame of a video.

20. The method for detecting and recognizing a license plate of claim 17 further comprising validating the set of characters recognized by the character recognition unit.