Systems and methods for mobile image capture and content processing of driver's licenses

• US 9,710,702 B2
• Filed: 03/28/2016
• Issued: 07/18/2017
• Est. Priority Date: 01/18/2008
• Status: Active Grant

• Current Assignee: Mitek Systems Incorporated
• Original Assignee: Mitek Systems Incorporated
• Inventors: Strange, Mike, Nepomniachtchi, Grigori
• Primary Examiner(s): MOTSINGER, SEAN T
• Application Number:
  US15/083,177
• Publication Number:
  US 20160283787A1
• Time in Patent Office: 477 Days
• CPC Class Codes: G06Q 20/3276 using a pictured code, e.g. barcode or QR-code, being read by the M-device
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1475 Inclination or skew detection or correction of characters or of image to be recognised
• CPC Class Codes: G06V 30/162 Quantising the image signal
• CPC Class Codes: G06V 30/166 Normalisation of pattern dimensions
• CPC Class Codes: G07C 2209/41 with means for the generation of identity documents
• CPC Class Codes: G07C 9/00 Individual registration on entry or exit
• CPC Class Codes: H04N 1/00244 with a server, e.g. an internet server fax-servers or the like for store and forward H04N1/324
• CPC Class Codes: H04N 1/00307 with a mobile telephone apparatus constructional features of portable telephone sets H04M1/0202; mobile radio systems H04W84/00
• CPC Class Codes: H04N 1/00708 Size or dimensions
• CPC Class Codes: H04N 1/00718 Skew
• CPC Class Codes: H04N 1/00734 Optical detectors
• CPC Class Codes: H04N 2101/00 Still video cameras
• CPC Class Codes: H04N 2201/001 Sharing resources, e.g. processing power or memory, with a connected apparatus or enhancing the capability of the still picture apparatus
• CPC Class Codes: H04N 2201/0084 Digital still camera

Abstract

Systems and methods are provided for processing and extracting content from an image of a driver'"'"'s license captured using a mobile device. In one embodiment, an image of a driver'"'"'s license (DL) is captured by a mobile device and corrected to improve the quality of the image. The corrected image is then further processed by cropping the image, identifying the format and layout of the DL, binarizing the image and extracting the content using optical character recognition (OCR). Multiple methods of image cropping may be implemented to accurately assess the borders of the DL, and a secondary layout identification process may be performed to ensure that the content being extracted is properly classified.

Claims

1. A computer-implemented method of processing an driver'"'"'s license image, comprising:

receiving an image captured by a mobile device, wherein the image includes a driver'"'"'s license image surrounded by a background portion;

performing a shape detection test on the image to produce a first set of coordinates representing a set of edges of the driver'"'"'s license image;

performing a rounded corner detection test on the image to produce a second set of coordinates associated with a set of corners of the driver'"'"'s license image;

combining the first set of coordinates and the second set of coordinates to generate a set of cropping parameters associated with borders of the driver'"'"'s license image;

cropping the image based at least on the cropping parameters to remove the background portion of the image to obtain the cropped driver'"'"'s license image;

binarizing the cropped driver'"'"'s license image to produce a binarized cropped driver'"'"'s license image; and

outputting the binarized cropped driver'"'"'s license image.

2. The computer-implemented method of claim 1, wherein prior to performing the rounded corner detection test on the image, the method further comprises pre-filtering the image using a low-pass noise suppression filter.

3. The computer-implemented method of claim 1, wherein the cropping parameters includes both coordinates associated with the set of corners of the driver'"'"'s license image and coordinates representing the set of edges of the driver'"'"'s license image.

4. The computer-implemented method of claim 1, wherein combining the first set of coordinates and the second set of coordinates includes selecting either the first set of coordinates or the second set of coordinates which is determined to be more accurately associated with the borders of the driver'"'"'s license image.

5. The computer-implemented method of claim 1, wherein generating the cropping parameters associated with the borders of the driver'"'"'s license image includes combining the first set of coordinates and the second set of coordinates with known information of a size and an aspect ratio of the driver'"'"'s license.

6. The computer-implemented method of claim 1, wherein the shape detection test includes a rectangular shape detection test.

7. The computer-implemented method of claim 1, wherein prior to combining the first set of coordinates and the second set of coordinates to generate the cropping parameters, the method further comprises performing a feature detection test on the image to produce a third set of coordinates associated with the set of corners of the driver'"'"'s license image.

8. The computer-implemented method of claim 7, wherein generating the set of cropping parameters associated with the borders of the driver'"'"'s license image further includes combining the first set of coordinates and the second set of coordinates with the third set of coordinates.

9. The computer-implemented method of claim 7, wherein performing the feature detection test on the image includes:

detecting a set of feature points in the image;

constructing a set of feature descriptors based on the set of feature points;

performing a feature matching operation between the set of feature descriptors and a set of predetermined features of a template driver'"'"'s license; and

generating the third set of coordinates based on outputs of the feature matching operating.

10. The computer-implemented method of claim 9, wherein detecting the set of feature points in the image includes detecting a set of local maxima in the image.

11. The computer-implemented method of claim 9, wherein constructing the set of feature descriptors based on the set of feature points includes computing local gradients and color distributions in the areas of the set of feature points.

12. The computer-implemented method of claim 9, wherein the outputs of the feature matching operation include a transformation matrix containing a set of matched feature points.

13. A system of processing an driver'"'"'s license image captured by a mobile device, comprising:

a processor;

a memory coupled to the processor;

a receiving unit which receives an image captured by a mobile device, wherein the image includes a driver'"'"'s license image surrounded by a background portion;

a shape detection unit which performs a shape detection test on the image to produce a first set of coordinates representing a set of edges of the driver'"'"'s license image;

a rounded-corner detection unit which performs a rounded corner detection test on the image to produce a second set of coordinates associated with a set of corners of the driver'"'"'s license image;

a cropping parameter generation unit which combines the first set of coordinates and the second set of coordinates to generate a set of cropping parameters associated with borders of the driver'"'"'s license image;

a cropping unit which crops the image based at least on the cropping parameters to remove the background portion of the image to obtain the cropped driver'"'"'s license image;

a binarization unit which binarizes the cropped driver'"'"'s license image to produce a binarized cropped driver'"'"'s license image; and

an output unit which outputs the binarized cropped driver'"'"'s license image.

14. The system of claim 13, further comprising a pre-filtering unit which pre-filters the image using a low-pass filter for noise suppression prior to performing the rounded corner detection test on the image.

15. The system of claim 13, wherein the cropping parameter generation unit is further configured to select either the first set of coordinates or the second set of coordinates which is determined to be more accurately associated with the borders of the driver'"'"'s license image.

16. The system of claim 13, wherein the cropping parameter generation unit is further configured to combine the first set of coordinates and the second set of coordinates with known information of a size and an aspect ratio of the driver'"'"'s license.

17. The system of claim 13, wherein the system further comprises a feature detection unit which performs a feature detection test on the image to produce a third set of coordinates associated with the set of corners of the driver'"'"'s license image.

18. The system of claim 17, wherein the cropping parameter generation unit is further configured to combine the first set of coordinates and the second set of coordinates with the third set of coordinates.

19. The system of claim 17, wherein the feature detection unit is configured to perform the feature detection test on the image by:

detecting a set of feature points in the image;

constructing a set of feature descriptors based on the set of feature points;

performing a feature matching operation between the set of feature descriptors and a set of predetermined features of a template driver'"'"'s license; and

generating the third set of coordinates based on outputs of the feature matching operating.

20. The system of claim 19, wherein the feature detection unit is configured to detect the set of feature points in the image by detecting a set of local maxima in the image.

21. The system of claim 19, wherein the feature detection unit is configured to construct the set of feature descriptors by computing local gradients and color distributions in the areas of the set of feature points.

22. A computer-implemented method of processing an driver'"'"'s license image, comprising:

receiving a image captured by a mobile device, wherein the image includes a driver'"'"'s license image surrounded by a background portion;

detecting a set of feature points in the image;

constructing a set of feature descriptors based on the set of detected feature points;

performing a feature matching operation between the set of feature descriptors and a set of predetermined features of a template driver'"'"'s license;

generating a set of coordinates representing a set of corners of the driver'"'"'s license image based on outputs of the feature matching operating;

cropping the image based at least on the set of coordinates to remove the background portion of the image to obtain the cropped driver'"'"'s license image;

binarizing the cropped driver'"'"'s license image to produce a binarized cropped driver'"'"'s license image; and

outputting the binarized cropped driver'"'"'s license image.

23. The computer-implemented method of claim 22, wherein detecting the set of feature points in the image includes detecting a set of local maxima in the image.

24. The computer-implemented method of claim 22, wherein constructing the set of feature descriptors based on the set of feature points includes computing local gradients and color distributions in the areas of the set of feature points.

25. The computer-implemented method of claim 22, wherein the outputs of the feature matching operation include a transformation matrix containing a set of matched feature points.